Agent-readable comparison

LibreChat vs Microsoft Copilot

Name: LibreChat vs Microsoft Copilot: agent-readable comparison
Creator: onAI

Published by onAI. onAI also sells one of the products compared here. Findings about other products link to public sources so you can check them; statements about onAI are marked as stated by onAI.

This comparison has 45 criteria with sourced findings for both products, including 45 that a second agent cross-checked for both. 51 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation: they are scoped, fresh and cite public resolved sources. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. "Stated by onAI" marks the publisher's own statements about its product (evidence type vendor-statement), which cite no third-party source. Humans approve the rubric, templates and generator; they do not review every finding. No winner is declared. A missing sourced finding is not evidence that a capability is absent.

LibreChat source checks: 2026-10-21 to 2026-10-26. Website: https://www.librechat.ai
Microsoft Copilot source checks: 2026-10-21 to 2026-10-26. Website: https://www.microsoft.com/en-us/microsoft-365-copilot
Generated 2026-10-27; next source check due 2026-12-20.

Same facts as Markdown and JSON. Methodology.

Models

MOD-01 Model catalogue and providers

Judgment rule: List each available model by provider and plan, including reasoning, fast and multimodal variants. Record whether the user picks the model, the product routes automatically, or both. A provider counts only if at least one of its current models is selectable on the scoped plan.

LibreChat

Agent cross-checked Support: partial

The model catalog is configured by the customer across first-party provider integrations and custom endpoints.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

providers: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access.
current_models: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account.
auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised.
multimodal_input: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested.

providers Which model providers are available? [partial]: Documented routes include OpenAI, Anthropic, Google, Azure OpenAI, AWS Bedrock and custom compatible services; selection requires enabled credentials and model access. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex.
current_models Which current models are selectable on this plan? [partial]: v0.8.8 release notes mention GPT-6/GPT-6.1 Sol, Claude Opus/Sonnet 5.5 and Gemini 3.8 Flash support. Actual selectable IDs still depend on the installed configuration and provider account. Sources: librechat:librechat:releases.
user_choice Can users pick the model per chat? [supported]: Users choose an endpoint/model unless admins enforce model specs or a fixed Agent. Sources: librechat:librechat:modelspec, librechat:librechat:agents.
auto_routing Does the product route between models automatically, and is the chosen model shown? [unknown]: auto_routing: Does the product route between models automatically, and is the chosen model shown? No automatic routing policy showing a chosen model was established, and no configured endpoint was exercised.
multimodal_input Which models accept images, audio or files? [partial]: Provider-native files support images/PDFs and some providers accept additional Office/audio/video types. Exact acceptance depends on the selected model and transport; no matrix was tested. Sources: librechat:librechat:ocr.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:ocr.

Microsoft Copilot

Agent cross-checked Support: partial

Commercial PowerPoint editing offers Auto, ChatGPT and Claude; this is not a catalogue for every Copilot chat or agent.

Availability: generally-available · Delivery: native
Scope: surfaces=Copilot in Microsoft 365 apps and Teams; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Commercial Microsoft Copilot subscription: PowerPoint editing mode only; add_ons=Eligible Microsoft 365/PowerPoint subscription, Commercial Microsoft Copilot subscription, Anthropic subprocessor enabled by the enterprise administrator for Claude; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Scope is commercial PowerPoint editing, with regional/subscription availability limits; no tenant picker or multimodal fixture was observed.
Cowork and Studio roadmap launches are separate experiences and are excluded from this current-model finding.

providers Which model providers are available? [supported]: PowerPoint editing names OpenAI ChatGPT and Anthropic Claude; the enterprise administrator must enable Anthropic before Claude appears. Sources: microsoft-copilot:ms-ppt-model-r2.
current_models Which current models are selectable on this plan? [partial]: This PowerPoint selector names ChatGPT and Claude, without versioned build IDs. GPT-6 Astra/Fable roadmap entries for Cowork/Studio do not establish PowerPoint or standalone Chat availability. Sources: microsoft-copilot:ms-ppt-model-r2.
user_choice Can users pick the model per chat? [supported]: In PowerPoint editing mode, the user chooses Auto, ChatGPT or Claude; the choice resets to Auto after the session. Sources: microsoft-copilot:ms-ppt-model-r2.
auto_routing Does the product route between models automatically, and is the chosen model shown? [partial]: PowerPoint Auto chooses a model; exact routed version and routing rationale are not established by this guide. Sources: microsoft-copilot:ms-ppt-model-r2.
multimodal_input Which models accept images, audio or files? [unknown]: Per-model image/audio/file modalities and a separate plan-specific standalone Chat picker remain unverified after reviewing PowerPoint selection and commercial model documentation.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-ppt-model-r2.

MOD-02 Model freshness

Judgment rule: Measure the days from a provider's general release to availability in the product for the last three major releases from OpenAI, Anthropic and Google (and Mistral where offered). Use dated changelogs or observation. Record deprecation notice for retired models.

LibreChat

Agent cross-checked Support: partial

Dated releases document model updates, but measured availability lags and retirement notice periods remain unknown.

Limitations

release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
version_pinning: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control.

release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: release_lag_days: What was the lag for each of the last three major releases, per provider? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
changelog Is there a dated public model changelog? [supported]: Public releases and the LibreChat changelog date model updates; v0.8.8 was published 2026-10-01. Sources: librechat:librechat:releases.
deprecation_notice How much notice is given before a model is removed? [unknown]: deprecation_notice: How much notice is given before a model is removed? No paired general-release/LibreChat-availability dates for the last three major releases per provider, or binding retirement-notice period, were established.
version_pinning Can an admin keep an older model version? [partial]: Admins can name explicit model IDs in endpoints/model specs; continuing remote availability remains under provider control. Sources: librechat:librechat:modelspec, librechat:librechat:custom.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:releases, librechat:librechat:modelspec, librechat:librechat:custom.

Microsoft Copilot

Agent cross-checked Support: partial

Dated release information exists; a comparable three-release lag series remains unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot Chat web app, Microsoft Copilot paid work chat, Copilot in Microsoft 365 apps and Teams, Microsoft Copilot desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Microsoft Copilot Chat with eligible Microsoft 365 subscription; paid Microsoft Copilot add-on where stated; add_ons=Qualifying Microsoft 365 base licence, Purview and SharePoint Advanced Management entitlements where stated, Copilot Credits usage-based billing for Cowork and other metered features where stated; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Unverified parts: release_lag_days, deprecation_notice, version_pinning.

release_lag_days What was the lag for each of the last three major releases, per provider? [unknown]: What was the lag for each of the last three major releases, per provider? Unverified after checking Microsoft release notes and AI at Work Roadmap; exact provider GA dates were not paired with three product release dates per provider.
changelog Is there a dated public model changelog? [supported]: Microsoft publishes dated product release notes and roadmap launches. Sources: microsoft-copilot:ms-release, microsoft-copilot:ms-roadmap.
deprecation_notice How much notice is given before a model is removed? [unknown]: How much notice is given before a model is removed? Unverified after checking Microsoft release notes and AI at Work Roadmap; exact provider GA dates were not paired with three product release dates per provider.
version_pinning Can an admin keep an older model version? [unknown]: Can an admin keep an older model version? Unverified after checking Microsoft release notes and AI at Work Roadmap; exact provider GA dates were not paired with three product release dates per provider.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-release, microsoft-copilot:ms-roadmap.

MOD-03 Bring-your-own keys and provider contracts

Judgment rule: Record customer-held API keys, customer cloud accounts (Azure OpenAI, Bedrock, Vertex), and aggregator routes (OpenRouter, LiteLLM) as separate routes. Record what still works without a vendor-provided model, whether prices change with BYO, and documented restrictions. API-key support does not imply support for the customer's own Azure contract.

LibreChat

Agent cross-checked Support: partial

Customer-held provider keys, customer Azure/AWS/Vertex configurations and custom endpoints are documented.

Limitations

byo_restrictions: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established.

own_api_keys Can the customer use its own provider API keys? [supported]: Provider keys can be operator-supplied or user_provided, with user key controls in Settings. Sources: librechat:librechat:firstchat, librechat:librechat:custom.
own_cloud_contract Can it use its own Azure OpenAI, Bedrock or Vertex deployment? [supported]: Customer Azure OpenAI deployments, AWS Bedrock region/credentials and Anthropic Vertex project/region routes are documented separately. Sources: librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex.
custom_endpoint Can an admin add any OpenAI-compatible endpoint? [supported]: Operators can configure a custom compatible API URL and model list. Sources: librechat:librechat:custom.
byo_pricing Does BYO change the licence price? [supported]: MIT repository use has no per-seat licence fee; customers separately procure provider service usage. Sources: librechat:librechat:license, librechat:librechat:firstchat.
byo_restrictions Which features stop working with BYO? [partial]: File modalities, tools and other capabilities depend on provider/model support and optional services. A universal BYO feature-parity guarantee was not established. Sources: librechat:librechat:ocr, librechat:librechat:code.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:custom, librechat:librechat:azure, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:license, librechat:librechat:ocr, librechat:librechat:code.

Microsoft Copilot

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

MOD-04 Local and self-hosted models

Judgment rule: Record support for models running in the customer's environment (vLLM, Ollama, TGI or similar) and which features work with them: chat, RAG, tools, embeddings. Distinguish a documented, supported route from a generic endpoint that happens to work.

LibreChat

Agent cross-checked Support: partial

Local compatible inference and Ollama embeddings are documented; optional services must also be local for a fully private stack.

Limitations

feature_parity: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run.
vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project.

self_hosted_chat Can chat use a customer-hosted model? [supported]: Custom endpoints can point at customer-hosted compatible model servers, including Ollama-compatible setups. Sources: librechat:librechat:custom.
self_hosted_embeddings Can retrieval use customer-hosted embeddings? [supported]: The RAG configuration documents Ollama embeddings and local Hugging Face through the appropriate full image. Sources: librechat:librechat:ragcfg.
feature_parity Which features fail with self-hosted models? [partial]: Chat and retrieval can use local endpoints. Tool calling and vision depend on the model; external OCR/search/code services are separate. No complete offline fixture was run. Sources: librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code.
vendor_hosted_open_models Does the vendor host open-weight models in EU/CH? [unknown]: vendor_hosted_open_models: Does the vendor host open-weight models in EU/CH? A vendor-hosted EU/Swiss open-weight model service was not established for the MIT self-hosted project.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:code.

Microsoft Copilot

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

MOD-05 Model control and usage limits

Judgment rule: Record admin allow-lists per group, default models, restrictions on which models may see which data, and per-user rate or fair-use limits. Test one restriction with two users in different groups. Record limits as enforced stops, warnings or undocumented fair use.

LibreChat

Agent cross-checked Support: partial

Model specs and scoped configuration can limit choices; optional user credit reservations provide a blocking mechanism.

Limitations

model_allowlist_by_group: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run.
data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides.
user_limits: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance.

model_allowlist_by_group Can admins limit models per group? [partial]: Enforced model specs and role/group configuration overrides can restrict available endpoints/models. The separate management UI is preview; a two-group fixture was not run. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access.
data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: data_bound_models: Can admins restrict which models receive connector or knowledge content? A hard binding between each enterprise content source and a permitted model provider was not established in the Agent and access-control guides.
default_model Can admins set the default model? [supported]: Model-spec presets can define default endpoint/model configurations. Sources: librechat:librechat:modelspec.
user_limits What per-user message or token limits apply, and are they published? [partial]: Balance tracking, initial credits/refills and message moderation limits are operator-configurable, rather than a universal vendor allowance. Sources: librechat:librechat:balance, librechat:librechat:mod.
limit_behaviour What happens when a limit is reached? [supported]: Pinned checkBalance reserves credits and throws a TOKEN_BALANCE error when insufficient. This establishes a blocking code path, not an observed end-to-end quota test. Sources: librechat:librechat:balance-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:admin, librechat:librechat:access, librechat:librechat:balance, librechat:librechat:mod, librechat:librechat:balance-pin.

Microsoft Copilot

Agent cross-checked Support: partial

Provider-level access and mode selection are documented; detailed quota and group tests remain open.

Limitations

No two-group model restriction test was performed.

model_allowlist_by_group Can admins limit models per group? [partial]: Admins select No users, All users or specific users/groups for Anthropic; this is provider-level rather than arbitrary per-model policy. Sources: microsoft-copilot:ms-anthropic.
data_bound_models Can admins restrict which models receive connector or knowledge content? [unknown]: Can admins restrict which models receive connector or knowledge content? Unverified after checking Microsoft Copilot privacy, commercial pricing, connector documentation, Agent Builder, and dated release notes on 2026-10-21; no licensed test tenant.
default_model Can admins set the default model? [unknown]: Can admins set the default model? Unverified after checking Microsoft Copilot privacy, commercial pricing, connector documentation, Agent Builder, and dated release notes on 2026-10-21; no licensed test tenant.
user_limits What per-user message or token limits apply, and are they published? [partial]: Chat provides standard access while paid Copilot has priority; numerical chat/token entitlements are not established here. Sources: microsoft-copilot:ms-price-us.
limit_behaviour What happens when a limit is reached? [unknown]: What happens when a limit is reached? Unverified after checking Microsoft Copilot privacy, commercial pricing, connector documentation, Agent Builder, and dated release notes on 2026-10-21; no licensed test tenant.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-anthropic, microsoft-copilot:ms-price-us.

Company knowledge

KNOW-01 Files in chat

Judgment rule: Record supported formats, size and count limits, scanned-PDF OCR, tables and spreadsheets, images inside documents, and whether a file is read in full or retrieved in chunks. Upload the shared fixture set (long German PDF, scanned contract, Excel with formulas, PowerPoint) and record failures.

LibreChat

Agent cross-checked Support: partial

Files can be indexed, injected as extracted text or sent directly to compatible model providers.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=New spreadsheet finding at development source a378657583567310c841d652b0f6b00c83e2bd6b; earlier accepted facts retain their cited release pins; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

File counts, sizes and provider acceptance depend on deployment settings.
Spreadsheet parsing yields named sheets and CSV values; layout/formula fidelity and the shared fixture remain untested.

formats Which formats are accepted? [supported]: Documents include PDF/text/Office formats through configured extraction; provider-native acceptance varies, including Bedrock Office formats and Google audio/video. Sources: librechat:librechat:ocr, librechat:librechat:filecfg.
limits What size and count limits apply per file and chat? [partial]: File counts, sizes and MIME patterns are operator/endpoint settings; provider limits may be stricter. The shared fixture was not uploaded. Sources: librechat:librechat:filecfg, librechat:librechat:ocr.
ocr Are scanned PDFs read? [supported]: Optional Mistral OCR, Azure/Vertex Mistral OCR and provider-native file processing are documented. Sources: librechat:librechat:ocr.
spreadsheets Are Excel tables read with structure intact? [partial]: The inspected built-in XLSX/XLS/ODS parser emits each sheet name and CSV values. The current guide lists a 15 MB built-in parser limit. Workbook formatting, formula recalculation and shared-fixture accuracy were not established. Sources: librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current.
full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [supported]: RAG retrieves indexed chunks; Upload as Text and Agent File Context inject extracted full text, subject to context limits. Sources: librechat:librechat:rag, librechat:librechat:text, librechat:librechat:ocr.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:ocr, librechat:librechat:filecfg, librechat:librechat:rag, librechat:librechat:text, librechat:librechat:r4-spreadsheet-parser, librechat:librechat:r4-text-current.

Microsoft Copilot

Agent cross-checked Support: partial

Documented upload formats and limits are available; fixture fidelity remains untested.

Limitations

Unverified parts: ocr, spreadsheets, full_vs_chunked.

formats Which formats are accepted? [supported]: PDF, DOCX, XLSX, PPTX; PNG/JPEG/PJP/JFIF; TXT/TEXT/JSON/CSV/MD. Sources: microsoft-copilot:ms-upload.
limits What size and count limits apply per file and chat? [supported]: Up to 20 files per conversation and 50 MB per file in the cited all-experiences support article. Sources: microsoft-copilot:ms-upload.
ocr Are scanned PDFs read? [unknown]: Are scanned PDFs read? Unverified after checking File upload in Microsoft Copilot; the long PDF, scanned contract, formula workbook and presentation fixtures were not run.
spreadsheets Are Excel tables read with structure intact? [unknown]: Are Excel tables read with structure intact? Unverified after checking File upload in Microsoft Copilot; the long PDF, scanned contract, formula workbook and presentation fixtures were not run.
full_vs_chunked Is the whole file used or only retrieved parts, and does the user see which? [unknown]: Is the whole file used or only retrieved parts, and does the user see which? Unverified after checking File upload in Microsoft Copilot; the long PDF, scanned contract, formula workbook and presentation fixtures were not run.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-upload.

KNOW-02 Knowledge bases and shared collections

Judgment rule: Record curated document collections that persist across chats, who can create and share them, size limits, and how they attach to assistants. Distinguish personal, group and organisation-wide scope.

LibreChat

Agent cross-checked Support: partial

Agents and personal Projects keep files across chats; shared Agent access is distinct from personal Project ownership.

Limitations

sharing_scope: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred.
size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent.

persistent_collections Can users keep document collections across chats? [supported]: Agent File Search/File Context and Project reference files persist for later chats. Sources: librechat:librechat:agents, librechat:librechat:projects.
sharing_scope Can collections be shared with users, groups or the whole organisation? [partial]: Agents can share files/knowledge with permitted users/groups/roles; Projects themselves are personal and cannot be shared or transferred. Sources: librechat:librechat:access, librechat:librechat:agents, librechat:librechat:projects.
size_limits What are the collection limits? [unknown]: size_limits: What are the collection limits? No universal collection storage/size allowance was established; limits are deployment and file-configuration dependent.
assistant_binding Can collections be bound to an assistant? [supported]: Agent File Search and File Context bind retrieved or extracted knowledge to an Agent. Sources: librechat:librechat:agents, librechat:librechat:ocr.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:projects, librechat:librechat:access, librechat:librechat:ocr.

Microsoft Copilot

Agent cross-checked Support: partial

Notebooks persist references and instructions, with plan-dependent reference limits.

Limitations

Read each atomic answer for its plan, access and feature limits.

persistent_collections Can users keep document collections across chats? [supported]: Copilot Notebooks retain selected reference collections. Sources: microsoft-copilot:ms-notebooks.
sharing_scope Can collections be shared with users, groups or the whole organisation? [partial]: Notebooks can be shared for collaborative editing; full user/group/organization sharing matrix was not verified. Sources: microsoft-copilot:ms-notebook-instructions.
size_limits What are the collection limits? [supported]: Chat notebook grounding uses up to 50 references; paid grounding uses up to 300, with broader supported entities. Sources: microsoft-copilot:ms-notebooks.
assistant_binding Can collections be bound to an assistant? [partial]: Agent Builder can bind SharePoint and connector knowledge; independent notebook-to-agent binding was not verified. Sources: microsoft-copilot:ms-builder.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-notebooks, microsoft-copilot:ms-notebook-instructions, microsoft-copilot:ms-builder.

KNOW-03 Enterprise connectors

Judgment rule: List each connector separately with plan, availability and setup owner: SharePoint, OneDrive, Outlook, Teams, Google Drive, Gmail, Confluence, Jira, Notion, Box, Salesforce, ServiceNow, file shares. Record whether the vendor or a third party (or the customer via MCP) provides it, and whether it needs admin consent. A connector listed on a roadmap or partner page is `announced`. An on-prem connector or gateway proves access to local data, not a self-hosted platform (DATA-02).

LibreChat

Agent cross-checked Support: partial

SharePoint and OneDrive have a documented delegated file picker. Other enterprise systems require separately verified tools or connectors.

Limitations

microsoft_365: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established.
google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
on_prem_sources: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [partial]: SharePoint Online and OneDrive for Business can be browsed and attached through Entra token reuse/OBO, delegated AllSites.Read and Files.Read.All, and admin consent. Outlook/Teams source access was not established. Sources: librechat:librechat:sharepoint.
google_workspace Which Google sources are connected? [unknown]: google_workspace: Which Google sources are connected? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
atlassian Confluence and Jira? [unknown]: atlassian: Confluence and Jira? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
other_systems Which other business systems? [unknown]: other_systems: Which other business systems? Google Drive/Gmail, Confluence/Jira and other named business-system connectors were not verified from first-party maintained connector documentation; generic MCP compatibility is not a connector catalog.
on_prem_sources Can on-prem file shares or databases be connected? [partial]: Custom local MCP stdio servers can reach systems available to the deployment, but a maintained file-share/database connector and its permissions were not verified. Sources: librechat:librechat:mcpcfg.
connector_provider Who builds and maintains each connector? [supported]: LibreChat documents the Microsoft picker. Other MCP tool integrations are separately configured and maintained by their respective server authors/operators. Sources: librechat:librechat:sharepoint, librechat:librechat:mcp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:sharepoint, librechat:librechat:mcpcfg, librechat:librechat:mcp.

Microsoft Copilot

Agent cross-checked Support: partial

Paid Copilot grounding supports synced and federated external sources; metered Copilot Chat agents have a narrower route.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat, Copilot in Microsoft 365 apps and Teams; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Microsoft Copilot add-on (Microsoft 365 Copilot in licensing docs), or Microsoft 365 E7; commercial tenant. Synced-data metered Chat agents are a separately identified route, not paid-work-chat parity.; add_ons=Eligible Microsoft 365 base subscription, Paid Microsoft Copilot add-on; called Microsoft 365 Copilot in some source pages, Source-service credentials/subscriptions and Purview entitlements where required; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

This is not a blanket connector entitlement for included Copilot Chat. The licence matrix permits Studio/pay-as-you-go synced data in agents only and excludes federation.
External-service subscriptions/permissions and connector-specific regional rollout remain prerequisites.

microsoft_365 Which M365 sources (SharePoint, OneDrive, Outlook, Teams) are connected? [supported]: Paid Copilot grounds on Microsoft Graph work content. Without that add-on, shared SharePoint/synced-connector data requires an eligible metered agent; ordinary Copilot Chat is not assigned equivalent grounding. Sources: microsoft-copilot:ms-privacy, microsoft-copilot:ms-connector-license-r2.
google_workspace Which Google sources are connected? [partial]: Google Drive is a synced connector for licensed Copilot grounding; the federated list includes Gmail for paid eligible users. Each source requires its own authorization. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2.
atlassian Confluence and Jira? [partial]: Confluence/Jira synced data can ground paid Copilot; their personal self-serve variants are limited preview. Metered agents can use synced data only, not the federated route. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-personal-sync-r2, microsoft-copilot:ms-connector-license-r2.
other_systems Which other business systems? [partial]: Synced examples include Box, Salesforce, ServiceNow, Dynamics365, Workday, Zendesk and SAP; this is the paid-grounding route, with source credentials and individual setup requirements. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-connector-license-r2.
on_prem_sources Can on-prem file shares or databases be connected? [supported]: File-share/SQL/Oracle sources can be indexed by a synced connector/connector agent for paid grounding or separately metered synced-data agents; this does not run Copilot on premises. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-connector-license-r2.
connector_provider Who builds and maintains each connector? [supported]: Microsoft/partner/custom synced connectors coexist. Federation can use Microsoft-published or approved partners, and custom MCP has its own admin setup. All federated querying requires the paid add-on/E7. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-custom-mcp-r2, microsoft-copilot:ms-connector-license-r2.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-privacy, microsoft-copilot:ms-connector-license-r2, microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-personal-sync-r2, microsoft-copilot:ms-custom-mcp-r2.

KNOW-04 Permission-aware retrieval

Judgment rule: Using two test users, verify that a restricted document in the fixture tenant is never cited or summarised for the user without access, including after a permission change. Record whether permissions are enforced at query time by the source system, mirrored into an index, or not enforced. Record the propagation delay of a revocation.

LibreChat

Agent cross-checked Support: partial

Product resource ACLs and delegated Microsoft file selection are documented. Continuing source permissions for copied content remain untested.

Limitations

source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
enforcement_point: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established.
revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
admin_scope_controls: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established.
sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.

source_permissions_respected Are source permissions enforced per user? [unknown]: source_permissions_respected: Are source permissions enforced per user? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [partial]: LibreChat ACLs control Agent/file resources; Microsoft delegated OBO limits source downloads as the signed-in user. No query-time source ACL check for previously copied chunks was established. Sources: librechat:librechat:access, librechat:librechat:sharepoint.
revocation_delay How quickly does a removed permission take effect? [unknown]: revocation_delay: How quickly does a removed permission take effect? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.
admin_scope_controls Can admins exclude sites, folders or labels? [partial]: Operators can scope Agent/resource grants and its selected files. Site/folder/label exclusion across sources was not established. Sources: librechat:librechat:access, librechat:librechat:agents.
sensitivity_labels Are Microsoft Purview or similar labels respected? [unknown]: sensitivity_labels: Are Microsoft Purview or similar labels respected? No restricted-document two-user fixture or grant/revocation test was run. Source permission enforcement, revocation delay and Purview label handling remain unverified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:sharepoint, librechat:librechat:agents.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft documents source-permission controls; the required restricted-document test was not run.

Limitations

All positive permission findings use the paid work-grounding route, not included Copilot Chat. Purview/SAM require their applicable entitlements.
No two-user restricted-document or revocation test; connector disable propagation is not proof of source-ACL revocation timing.

source_permissions_respected Are source permissions enforced per user? [supported]: In licensed Copilot work grounding, Graph data is limited to the requesting user's access; this was not tested. Sources: microsoft-copilot:ms-privacy, microsoft-copilot:ms-connector-license-r2.
enforcement_point Does the source system, a mirrored index or nothing enforce them? [supported]: Paid synced grounding filters item ACLs in Graph; paid federated access executes with the authenticated source-user identity. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2.
revocation_delay How quickly does a removed permission take effect? [unknown]: How quickly does a removed permission take effect? Unverified after checking Copilot privacy, connector architecture and Purview DLP; no two-user or permission-revocation fixture.
admin_scope_controls Can admins exclude sites, folders or labels? [supported]: Licensed Copilot deployment guidance documents restricted SharePoint search/SAM; federated access also intersects tenant User access and connector staging. Sources: microsoft-copilot:ms-setup, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2.
sensitivity_labels Are Microsoft Purview or similar labels respected? [supported]: Purview can exclude labelled content from processing through configured DLP rules. Sources: microsoft-copilot:ms-dlp.

KNOW-05 Freshness and sync model

Judgment rule: Record live (federated) search versus a copied index, sync interval, deletion propagation, and where the index is stored. Edit and delete one fixture document and record when answers change. A copied index adds storage location to DATA-01.

LibreChat

Agent cross-checked Support: partial

The RAG API copies uploaded content into PGVector; imported files do not by themselves establish live enterprise synchronization.

Limitations

sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.

live_or_indexed Is content searched live or copied into an index? [supported]: The RAG API indexes uploaded documents into PostgreSQL/PGVector; file-context mode stores extracted text in Agent instructions. Sources: librechat:librechat:rag, librechat:librechat:ocr.
sync_interval How often does an index refresh? [unknown]: sync_interval: How often does an index refresh? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
deletion_propagation How quickly does a deleted document disappear? [unknown]: deletion_propagation: How quickly does a deleted document disappear? No periodic enterprise-source sync contract, source edit/delete propagation bound or timed fixture was established from the RAG and Microsoft import guides.
index_location Where is indexed content stored? [supported]: The operator chooses the RAG database and its location, independently of the inference provider. Sources: librechat:librechat:rag, librechat:librechat:compose-pin.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:ocr, librechat:librechat:compose-pin.

Microsoft Copilot

Agent cross-checked Support: partial

Both copied Graph indexes and live MCP federation are documented.

Limitations

Copilot Chat without the add-on is not included as a general indexed/federated grounding entitlement.
No edit/delete propagation fixture; self-serve Confluence/Jira remains limited preview.

live_or_indexed Is content searched live or copied into an index? [supported]: Licensed Copilot can ground on synced Graph copies or query federated sources live without a separate external-content index. The licence matrix allows metered Chat agents to use synced data only. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2.
sync_interval How often does an index refresh? [partial]: For the limited-preview personal Confluence/Jira synced route, docs describe roughly15-minute incremental and seven-day full crawls; this is not a general federated or connector SLA. Sources: microsoft-copilot:ms-personal-sync-r2, microsoft-copilot:ms-connector-license-r2.
deletion_propagation How quickly does a deleted document disappear? [unknown]: How quickly does a deleted document disappear? Unverified after checking connector overview and personal-sync documentation; no edit/delete propagation fixture.
index_location Where is indexed content stored? [partial]: Paid synced grounding uses the Microsoft365 tenant Graph cloud index; federation does not copy that external content into an index. A country-level index map remains unverified. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2, microsoft-copilot:ms-personal-sync-r2.

KNOW-06 Grounding and retrieval quality

Judgment rule: Run the shared question set over the fixture corpus: factual lookups, cross-document questions, German document with an English question, a question with no answer in the corpus. Record citation presence, link accuracy, correct answers and refusals to invent. Disclose model, settings, attempt count and failures. Single runs support a case study, not a ranking.

LibreChat

Agent cross-checked Support: partial

File-search citations are documented; retrieval accuracy remains unmeasured.

Limitations

citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.

citations Are answers linked to specific sources? [supported]: RAG/File Search provides retrieved source references and citation controls. Sources: librechat:librechat:rag, librechat:librechat:access.
citation_accuracy Do the cited passages support the answer? [unknown]: citation_accuracy: Do the cited passages support the answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
cross_language Does a question in one language find documents in another? [unknown]: cross_language: Does a question in one language find documents in another? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
no_answer_behaviour Does it say when the corpus has no answer? [unknown]: no_answer_behaviour: Does it say when the corpus has no answer? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.
observed_accuracy How many of the question set were answered correctly? [unknown]: observed_accuracy: How many of the question set were answered correctly? The shared multilingual factual/cross-document/no-answer question set was not run. Citation correctness, cross-language success, no-answer reliability and observed accuracy remain unknown.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:rag, librechat:librechat:access.

Microsoft Copilot

Agent cross-checked Support: partial

Source links are documented; retrieval quality and cross-language accuracy remain unmeasured.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Microsoft Copilot/E7 connector-grounded responses only; add_ons=Eligible Microsoft 365 base subscription, Paid Microsoft Copilot add-on; called Microsoft 365 Copilot in some source pages, Source-service credentials/subscriptions and Purview entitlements where required; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Documented citations apply to the licensed connector-grounding route; no equivalent included-Chat entitlement or measured citation accuracy is claimed.
No DE/FR/EN grounding, cross-language, unanswerable-question or restricted-document fixture was run.

citations Are answers linked to specific sources? [supported]: For licensed Copilot connector-grounded responses, Microsoft documents source citations and links to referenced external items. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-connector-license-r2.
citation_accuracy Do the cited passages support the answer? [unknown]: Do the cited passages support the answer? Unverified after checking connector response documentation; no shared DE/FR/EN corpus or answer set was executed.
cross_language Does a question in one language find documents in another? [unknown]: Does a question in one language find documents in another? Unverified after checking connector response documentation; no shared DE/FR/EN corpus or answer set was executed.
no_answer_behaviour Does it say when the corpus has no answer? [unknown]: Does it say when the corpus has no answer? Unverified after checking connector response documentation; no shared DE/FR/EN corpus or answer set was executed.
observed_accuracy How many of the question set were answered correctly? [unknown]: How many of the question set were answered correctly? Unverified after checking connector response documentation; no shared DE/FR/EN corpus or answer set was executed.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-connector-license-r2.

KNOW-07 Memory and personal context

Judgment rule: Record personal custom instructions, cross-chat memory, project or workspace context, and user controls to view, edit, delete or disable memory. Record whether admins can disable memory organisation-wide.

LibreChat

Agent cross-checked Support: supported

Opt-in user memory stores editable key/value context across chats; Projects and Agents provide additional persistent instructions.

custom_instructions Can users set persistent instructions? [supported]: Projects retain instructions across their chats; Agents retain system instructions. Sources: librechat:librechat:projects, librechat:librechat:agents.
cross_chat_memory Does the product remember facts across chats? [supported]: User Memory injects configured key/value entries across chats and is not semantic search over all past conversations. Sources: librechat:librechat:memory.
user_memory_controls Can users view, edit and delete memories? [supported]: Users add/edit/remove entries and can toggle memory when permitted. Sources: librechat:librechat:memory.
admin_memory_controls Can admins turn memory off? [supported]: Memory is disabled until configured and its feature permissions can be restricted by role. Sources: librechat:librechat:memory, librechat:librechat:access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:projects, librechat:librechat:agents, librechat:librechat:memory, librechat:librechat:access.

Microsoft Copilot

Agent cross-checked Support: partial

Saved memory, history-based personalization and instructions have user controls.

Limitations

Unverified parts: admin_memory_controls.
Read each atomic answer for its plan, access and feature limits.

custom_instructions Can users set persistent instructions? [supported]: Users set personal instructions; notebooks have their own instructions. Sources: microsoft-copilot:ms-memory, microsoft-copilot:ms-notebook-instructions.
cross_chat_memory Does the product remember facts across chats? [supported]: Enabled memory stores preferences and can use prior-chat inferences; work insights depend on plan. Sources: microsoft-copilot:ms-memory.
user_memory_controls Can users view, edit and delete memories? [partial]: Users can inspect what Copilot knows, ask it to forget details and use temporary chat. Complete saved-memory editing behavior was not tested. Sources: microsoft-copilot:ms-memory.
admin_memory_controls Can admins turn memory off? [unknown]: Can admins turn memory off? Unverified after checking personalization documentation and Copilot management; organization-wide memory policy behavior not independently established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-memory, microsoft-copilot:ms-notebook-instructions.

Assistants and agents

AGT-01 Custom assistants

Judgment rule: Record creation of assistants with instructions, model, knowledge and tools; who can create; sharing scope; versioning; and an internal catalogue or directory. Build one HR policy assistant on the fixture and share it with one group. Prompt templates and a prompt library are recorded here.

LibreChat

Agent cross-checked Support: supported

Agents combine instructions, a model, knowledge and tools, with version history and a permissioned internal catalog.

create_assistants Can users create assistants with instructions, knowledge and tools? [supported]: The Agent Builder creates reusable instructions/model/files/tools/skills configurations. Sources: librechat:librechat:agents.
creator_permissions Can admins limit who creates them? [supported]: AGENTS CREATE and sharing permissions can be restricted by role; resource grants control access. Sources: librechat:librechat:access.
sharing_scope Can assistants be shared with users, groups or everyone? [supported]: Agent ACLs support users, groups, roles and all authenticated users when public sharing is permitted. Sources: librechat:librechat:access.
catalogue Is there an internal assistant directory? [supported]: Agents have a marketplace/catalog and searchable builder tool library. Sources: librechat:librechat:agents.
prompt_library Are shared prompt templates available? [supported]: Prompt resources have use/create/share/share-public permissions and ACLs. Sources: librechat:librechat:access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:access.

Microsoft Copilot

Agent cross-checked Support: partial

Agent Builder and the agent catalogue cover shared assistants; external actions need a different authoring route.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat, Microsoft Copilot Chat web app, Copilot Studio extension and agent builder, separate licensing where stated; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Microsoft Copilot Chat with eligible Microsoft 365 subscription; paid Microsoft Copilot add-on where stated; add_ons=Qualifying Microsoft 365 base licence, Purview and SharePoint Advanced Management entitlements where stated, Copilot Credits usage-based billing for Cowork and other metered features where stated; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Read each atomic answer for its plan, access and feature limits.

create_assistants Can users create assistants with instructions, knowledge and tools? [partial]: Agent Builder combines instructions and selected knowledge; external action authoring requires Copilot Studio. Sources: microsoft-copilot:ms-builder.
creator_permissions Can admins limit who creates them? [supported]: Admins control whether users can access Agent Builder. Sources: microsoft-copilot:ms-builder.
sharing_scope Can assistants be shared with users, groups or everyone? [partial]: Agent links can be shared; the complete user/group/organization permission matrix was not checked. Sources: microsoft-copilot:ms-agents.
catalogue Is there an internal assistant directory? [supported]: The app lists prebuilt, shared and organization agents. Sources: microsoft-copilot:ms-agents.
prompt_library Are shared prompt templates available? [supported]: The commercial page links Copilot Prompt Gallery. Sources: microsoft-copilot:ms-price-us.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-builder, microsoft-copilot:ms-agents, microsoft-copilot:ms-price-us.

AGT-02 Tools, actions and MCP

Judgment rule: Record built-in tools, custom actions (OpenAPI), MCP client support (local and remote servers), authentication model per tool (shared service account or per-user OAuth), and admin approval of tools. Verify one external-tool call and its access boundary.

LibreChat

Agent cross-checked Support: partial

Agent tools include file search, code, web and Actions, with local/remote MCP and configurable approval boundaries.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Customer-operated or third-party MCP servers, Optional separate Code Interpreter service; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

tool_approval: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised.

builtin_tools Which tools are built in? [supported]: Agent capabilities include file search/context, web search, memory and optionally configured code execution/image tools. Sources: librechat:librechat:agents, librechat:librechat:images.
custom_actions Can admins add API actions? [supported]: Agents support custom API Actions configured in the tool library. Sources: librechat:librechat:agents.
mcp_client Can it use remote MCP servers, and with what admin control? [supported]: Configured MCP transports include stdio, SSE and Streamable HTTP; YAML and permissioned UI setup are documented. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg.
tool_auth Do tools act as the user or as a shared account? [supported]: MCP supports configured credentials/headers and OAuth; credential and resource ownership scope depends on each server configuration. Sources: librechat:librechat:mcp, librechat:librechat:mcpcfg.
tool_approval Can admins approve or block tools, and can users confirm actions before they run? [partial]: Agent/code environments document approval modes and individual tool-call approvals. The default policy and every external side-effect boundary were not exercised. Sources: librechat:librechat:agents, librechat:librechat:code.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:images, librechat:librechat:mcp, librechat:librechat:mcpcfg, librechat:librechat:code.

Microsoft Copilot

Agent cross-checked Support: partial

Paid Copilot documents authenticated MCP tools and conditional writes; the October16 detailed guide supersedes the older generic read-only rollout description.

Availability: unknown · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat, Copilot Studio extension and agent builder, separate licensing where stated; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Microsoft Copilot/E7 federated connectors and paid Copilot Agent Builder; Studio is only the separately licensed extension route; add_ons=Eligible Microsoft 365 base subscription, Paid Microsoft Copilot add-on; called Microsoft 365 Copilot in some source pages, Source-service credentials/subscriptions and Purview entitlements where required; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Reconciliation: October6 overview retains read-only/early-October text; October16 detailed federation/setup pages explicitly document writes. The current finding is conditional protocol behavior, with actual tenant write availability unknown.
Researcher has an explicit read-only boundary. No external call, approval or access-boundary fixture was executed.

builtin_tools Which tools are built in? [supported]: Paid experiences include Researcher, Analyst and Facilitator. Sources: microsoft-copilot:ms-price-us.
custom_actions Can admins add API actions? [partial]: Agent Builder directs authored external-action scenarios to Copilot Studio. Separately, paid federated MCP connectors can expose create/update/delete tools where supplied by the publisher. Sources: microsoft-copilot:ms-builder, microsoft-copilot:ms-custom-mcp-r2, microsoft-copilot:ms-federated-r2.
mcp_client Can it use remote MCP servers, and with what admin control? [supported]: Custom federation accepts a remote MCP server with search/fetch/query and optional create/update/delete tools. Federation requires the querying user's paid add-on/E7; Studio/pay-as-you-go alone is insufficient. Sources: microsoft-copilot:ms-custom-mcp-r2, microsoft-copilot:ms-connector-license-r2.
tool_auth Do tools act as the user or as a shared account? [supported]: Federated authenticated tools use OAuth/source-user identity and source permissions. Tenant User access, publisher controls and staged rollout also apply. Sources: microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-custom-mcp-r2.
tool_approval Can admins approve or block tools, and can users confirm actions before they run? [partial]: Where a connector supplies writes, October16 docs require initial explicit approval with per-tool Allow once/conversation/Always allow settings. Researcher remains read-only. The Coming soon label concerns the admin Tools list. Sources: microsoft-copilot:ms-federated-r2.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-builder, microsoft-copilot:ms-custom-mcp-r2, microsoft-copilot:ms-federated-r2, microsoft-copilot:ms-connector-license-r2.

AGT-03 Web search and deep research

Judgment rule: Record web search on/off control per organisation and group, search provider, citation of web sources, deep or multi-step research, and whether queries leave the residency boundary. Admins of regulated companies often need web search off.

LibreChat

Agent cross-checked Support: partial

Web search combines configured search, scraping and optional reranking services; source queries can leave the installation boundary.

Limitations

deep_research: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified.

web_search Is web search available? [supported]: Tool-capable chats/Agents can use the configured web search capability. Sources: librechat:librechat:web, librechat:librechat:agents.
admin_toggle Can admins disable it per organisation or group? [supported]: WEB_SEARCH feature permissions control use; operators configure whether its provider stack is available. Sources: librechat:librechat:access, librechat:librechat:web.
search_provider Which search provider handles queries, and where? [supported]: Documented choices include Serper, SearXNG, Tavily and Keenable, with Firecrawl/Tavily/Keenable scraping and optional Jina/Cohere reranking. Geography depends on the chosen services. Sources: librechat:librechat:web.
deep_research Is multi-step research with a report available? [partial]: Agents can perform repeated tool operations and web research. No dedicated report fixture, quality result or preset research SLA was verified. Sources: librechat:librechat:agents, librechat:librechat:web.
web_citations Are web sources cited? [supported]: The web-search guide documents source references/citations from search and fetched content. Sources: librechat:librechat:web.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:web, librechat:librechat:agents, librechat:librechat:access.

Microsoft Copilot

Agent cross-checked Support: supported

Web search is policy-controlled and uses Bing outside the Microsoft 365 search-query boundary.

web_search Is web search available? [supported]: Chat can ground answers in web search. Sources: microsoft-copilot:ms-chat-privacy.
admin_toggle Can admins disable it per organisation or group? [supported]: Allow web search can target the tenant, groups or users. Sources: microsoft-copilot:ms-manage.
search_provider Which search provider handles queries, and where? [supported]: Bing receives generated queries under separate data-handling terms; those queries are outside EUDB. Sources: microsoft-copilot:ms-chat-privacy.
deep_research Is multi-step research with a report available? [supported]: Researcher is included in paid Copilot; a report fixture was not run. Sources: microsoft-copilot:ms-price-us.
web_citations Are web sources cited? [supported]: Responses include web citations and show generated query details for 24 hours. Sources: microsoft-copilot:ms-chat-privacy.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-chat-privacy, microsoft-copilot:ms-manage, microsoft-copilot:ms-price-us.

AGT-04 Workflows and automation

Judgment rule: Record no-code or low-code workflows, scheduled prompts, triggers from email, forms or business systems, and multi-step chains. Name where they run and who can build them. A shared prompt template is not a workflow.

LibreChat

Agent cross-checked Support: partial

Experimental Scheduled Chats run saved Agents on cron schedules; beta Agent Events can receive external deliveries.

Availability: beta · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Experimental schedules explicitly enabled, Beta Agents API for external Agent Events; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

workflow_builder: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established.
event_triggers: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified.

workflow_builder Is there a workflow or chain builder? [partial]: Agent Builder supports tool workflows and subagent configurations; no general business no-code flow editor was established. Sources: librechat:librechat:agents.
scheduled_tasks Can prompts or assistants run on a schedule? [supported]: Scheduled Chats supports hourly/daily/weekly/custom cron with time zones, owner scope and execution checks; it is experimental and off by default. Sources: librechat:librechat:schedule.
event_triggers Can external events start a workflow? [partial]: The beta Agents API includes authenticated Agent Events. A built-in email/form trigger catalog was not verified. Sources: librechat:librechat:api.
builder_audience Is building aimed at business users, IT or developers? [supported]: Agent Builder is a user UI; API-event and runtime configuration require technical deployment work. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:schedule, librechat:librechat:api.

Microsoft Copilot

Agent cross-checked Support: partial

Paid Copilot schedules prompts; advanced workflow authoring has separate Studio dependencies.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat, Copilot Studio extension and agent builder, separate licensing where stated; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Microsoft Copilot Chat with eligible Microsoft 365 subscription; paid Microsoft Copilot add-on where stated; add_ons=Qualifying Microsoft 365 base licence, Purview and SharePoint Advanced Management entitlements where stated, Copilot Credits usage-based billing for Cowork and other metered features where stated; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Unverified parts: event_triggers.
Read each atomic answer for its plan, access and feature limits.

workflow_builder Is there a workflow or chain builder? [partial]: Agent Builder directs low-code actions and workflows to Copilot Studio. Sources: microsoft-copilot:ms-builder.
scheduled_tasks Can prompts or assistants run on a schedule? [supported]: Paid users can create up to ten scheduled prompts and manage their recurrence. Sources: microsoft-copilot:ms-schedule.
event_triggers Can external events start a workflow? [unknown]: Can external events start a workflow? Unverified after checking scheduled prompt and Agent Builder documentation; external-event trigger availability was not scoped.
builder_audience Is building aimed at business users, IT or developers? [supported]: Agent Builder uses natural-language configuration; Studio is the low-code extension route. Sources: microsoft-copilot:ms-builder.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-builder, microsoft-copilot:ms-schedule.

AGT-05 Agentic task execution

Judgment rule: Record an agent mode that plans and carries out multi-step tasks with tools (browser, files, connectors), with visible steps, user confirmation of side effects and stop control. Run one fixture task (gather three documents, draft a summary, propose an email). Record interventions and what ran. A final claim of success is not proof.

LibreChat

Agent cross-checked Support: partial

Agent runs expose reasoning/tool activity and optional approval, interruption and cooperative stop controls.

Limitations

No gather-documents, draft-summary and propose-email task was run.
Highly experimental attached workspaces are distinct from ordinary Agent tool use.

agent_mode Is there an agent mode for multi-step tasks? [supported]: Agents execute multi-step tool workflows; code/workspace capabilities require a compatible separately deployed service. Sources: librechat:librechat:agents, librechat:librechat:code.
visible_steps Are steps and tool calls shown? [supported]: Activity groups and tool cards distinguish preparation, execution, completion, cancellation and failure. Sources: librechat:librechat:agents.
side_effect_confirmation Must the user confirm actions with side effects? [partial]: Attached environments can expose Ask before changes/Accept edits/Full access, bounded by operator tool rules. This is configurable, not a guarantee that all side effects require confirmation. Sources: librechat:librechat:agents, librechat:librechat:code.
stop_control Can the user stop a running task? [partial]: The release documents interruption/steering; ordinary background-tool cancellation is optional and cooperative, so an uncooperative tool may still finish. Sources: librechat:librechat:agents, librechat:librechat:releases.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:code, librechat:librechat:releases.

Microsoft Copilot

Agent cross-checked Support: partial

Cowork documents multi-step tool execution with visible progress and user controls.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat, Microsoft Copilot desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Microsoft Copilot with Cowork enabled; add_ons=Qualifying Microsoft 365 licence, Enabled usage-based Cowork billing; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Documented behavior only; no three-document/email fixture or interventions were observed.

agent_mode Is there an agent mode for multi-step tasks? [supported]: Cowork handles multi-step work with enabled usage billing and a paid licence. Sources: microsoft-copilot:ms-cowork.
visible_steps Are steps and tool calls shown? [supported]: The interface exposes skill messages and tool steps. Sources: microsoft-copilot:ms-cowork.
side_effect_confirmation Must the user confirm actions with side effects? [supported]: Side effects require approval; users can allow similar actions for the current session. Sources: microsoft-copilot:ms-cowork.
stop_control Can the user stop a running task? [supported]: Users can pause immediately or after the current step, resume or cancel. Sources: microsoft-copilot:ms-cowork.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-cowork.

AGT-06 Programmable access

Judgment rule: Record a public API for chat, assistants and knowledge, SDKs, API authentication, rate limits and whether API use counts against the same governance (audit, budgets, model restrictions). Being an MCP client is different from exposing the product over MCP.

LibreChat

Agent cross-checked Support: partial

The beta Agents API provides inference, Agent management and authenticated events; deployment guards and limitations are explicit.

Availability: beta · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

knowledge_api: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified.
api_governance: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested.
mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface.

chat_api Is there an API for chat and assistants? [supported]: Chat Completions and Open Responses interfaces expose saved Agents, with API-key or configured OIDC authentication. Sources: librechat:librechat:api.
knowledge_api Can documents be loaded through an API? [partial]: The beta management surface includes Agent/Skill management. A complete public knowledge-ingestion contract and fixture were not verified. Sources: librechat:librechat:api.
api_governance Do audit, budgets and model rules apply to API use? [partial]: Agent access and remote-agent permissions gate APIs, with source identity bound for events. Complete logging/budget/model parity across routes was not tested. Sources: librechat:librechat:api, librechat:librechat:access.
mcp_server Does the product expose itself to other agents over MCP? [unknown]: mcp_server: Does the product expose itself to other agents over MCP? A native product-wide MCP server was not established; being an MCP client does not establish that interface.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:api, librechat:librechat:access.

Microsoft Copilot

Agent cross-checked Support: partial

The Chat API and the Work IQ API public preview are separate programmable routes.

Availability: beta · Delivery: native
Scope: surfaces=Microsoft Copilot Chat API preview, Work IQ API public preview, MCP/A2A/REST; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Chat API preview requires the paid Copilot add-on per calling user; Work IQ MCP public-preview prerequisites unverified; add_ons=Eligible Microsoft 365 base subscription, Paid Microsoft Copilot add-on; called Microsoft 365 Copilot in some source pages, Source-service credentials/subscriptions and Purview entitlements where required; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

API preview terms apply. This is a distinct API surface, not included Copilot Chat or an assertion of interactive/API feature parity. No API call was executed.
Work IQ MCP is a roadmap-described public preview; no endpoint or API was invoked.

chat_api Is there an API for chat and assistants? [partial]: The preview text API is included for paid-add-on users; unlicensed users are explicitly excluded. It supports work/web grounding but not code interpreter, graphic art, action skills or long-running tasks. Sources: microsoft-copilot:ms-chat-api-r2.
knowledge_api Can documents be loaded through an API? [partial]: Separately configured synced content can be ingested through Graph connector APIs for licensed grounding; this does not establish a complete workspace knowledge-management API. Sources: microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-connector-license-r2.
api_governance Do audit, budgets and model rules apply to API use? [partial]: The Chat API retains source-permission/compliance boundaries; full budget/audit parity was not independently tested. Sources: microsoft-copilot:ms-chat-api-r2.
mcp_server Does the product expose itself to other agents over MCP? [partial]: Microsoft advertises Work IQ API public preview with MCP, A2A and REST access to work context. Endpoint, authentication and plan details were not verified; this does not make the separate Copilot Chat API an MCP server. Sources: microsoft-copilot:microsoft-copilot:r4-roadmap-work-iq.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:ms-chat-api-r2, microsoft-copilot:ms-connectors-r2, microsoft-copilot:ms-connector-license-r2, microsoft-copilot:microsoft-copilot:r4-roadmap-work-iq.

Daily work

WORK-01 Clients and access points

Judgment rule: List web, desktop (Windows, macOS), iOS, Android, mobile browser and browser extension separately. For each, record login with company SSO, feature gaps against web, and MDM/Intune deployability. An installable app is different from a mobile website.

LibreChat

Agent cross-checked Support: partial

The main deployment is a responsive browser client. Native clients, MDM and a supported sidebar extension were not verified.

Limitations

desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
mobile_apps: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established.
browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
client_feature_gaps: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested.

web Is a full web client available? [supported]: A Docker/npm deployment serves a browser application at the configured server URL. Sources: librechat:librechat:firstchat, librechat:librechat:local.
desktop_apps Windows and macOS apps? [unknown]: desktop_apps: Windows and macOS apps? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
mobile_apps iOS and Android apps with SSO? [partial]: Docs describe mobile navigation and temporary-chat controls in the web UI. No native iOS/Android client with company SSO was established. Sources: librechat:librechat:retention, librechat:librechat:insights.
browser_extension Is there a browser extension or sidebar? [unknown]: browser_extension: Is there a browser extension or sidebar? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
managed_deployment Can IT deploy and configure clients through MDM? [unknown]: managed_deployment: Can IT deploy and configure clients through MDM? The self-host installation and client docs did not establish native Windows/macOS apps, a first-party browser extension or Intune/MDM configuration.
client_feature_gaps Which features are missing on mobile? [partial]: Desktop/mobile layouts expose different navigation controls; no comprehensive parity matrix was tested. Sources: librechat:librechat:retention, librechat:librechat:insights.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:firstchat, librechat:librechat:local, librechat:librechat:retention, librechat:librechat:insights.

Microsoft Copilot

Agent cross-checked Support: partial

Web and native access are documented, with authoring gaps on mobile.

Limitations

Windows MDM deployment is documented; full mobile deployment/configuration parity was not tested.

web Is a full web client available? [supported]: The browser client is available for paid Copilot and Copilot Chat. Sources: microsoft-copilot:ms-price-us.
desktop_apps Windows and macOS apps? [supported]: Cowork documentation lists Windows and macOS Copilot clients. Sources: microsoft-copilot:ms-cowork.
mobile_apps iOS and Android apps with SSO? [partial]: Cowork lists iPhone and Android apps under the licensed account; mobile SSO was not trialled. Sources: microsoft-copilot:ms-cowork.
browser_extension Is there a browser extension or sidebar? [partial]: Copilot is available in the Edge sidebar; this does not establish a separate third-party browser extension. Sources: microsoft-copilot:ms-chat-usage.
managed_deployment Can IT deploy and configure clients through MDM? [supported]: For Windows, IT can distribute the Copilot executable through Intune, Configuration Manager, Group Policy or another MDM and control automatic installation. EEA, government and channel exclusions apply to automatic installation; full mobile policy parity was not tested. Sources: microsoft-copilot:microsoft-copilot:r4-mdm-deployment.
client_feature_gaps Which features are missing on mobile? [partial]: Agent Builder is unavailable on mobile; other feature differences vary by release. Sources: microsoft-copilot:ms-builder.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-cowork, microsoft-copilot:ms-chat-usage, microsoft-copilot:ms-builder, microsoft-copilot:microsoft-copilot:r4-mdm-deployment.

WORK-02 Office suite and Teams integration

Judgment rule: Record presence inside Word, Excel, PowerPoint, Outlook and Teams (and Google Docs, Gmail), with what the assistant can do in each: read the open document, write into it, act on mail. Record extra licences and admin consent needed. A connector that searches Office files is KNOW-03, not WORK-02.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Microsoft Copilot

Agent cross-checked Support: partial

The paid offering works inside Microsoft 365 apps; Chat has narrower contextual access.

Limitations

Unverified parts: google_workspace_apps.

word_excel_powerpoint Does it work inside Word, Excel and PowerPoint? [supported]: Paid Copilot is integrated in Word, Excel and PowerPoint; Chat open-content interactions are narrower. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-chat-privacy.
outlook Does it work inside Outlook? [supported]: Chat in Outlook can use the user mailbox/calendar and a limited set of accessible files. Sources: microsoft-copilot:ms-chat-privacy.
teams Is there a Teams app or bot? [supported]: Paid Copilot includes Teams; the Chat entry point also appears in Teams. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-chat-usage.
google_workspace_apps Does it work inside Docs, Sheets or Gmail? [unknown]: Does it work inside Docs, Sheets or Gmail? Unverified after checking pricing, Chat organizational-data and deployment documentation; native Google Workspace editing integrations not established.
licence_prerequisites Which licences or consents are needed? [supported]: Paid Copilot requires an eligible M365 base licence; compliance capabilities may need further entitlements. Sources: microsoft-copilot:ms-setup.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-chat-privacy, microsoft-copilot:ms-chat-usage, microsoft-copilot:ms-setup.

WORK-03 Translation and writing

Judgment rule: Record document translation preserving layout, the translation engine (LLM or dedicated such as DeepL), glossaries, formality control, supported languages including Swiss German conventions (no ß), and rewriting/proofreading tools. Translate the shared German contract into French and Italian and record layout and glossary results.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Microsoft Copilot

Agent cross-checked Support: partial

Copilot Chat can translate referenced document text and accept tone/audience instructions. Format-preserving Word Translator and SharePoint glossary translation are separately scoped workflows.

Availability: generally-available · Delivery: native
Scope: surfaces=Copilot in Microsoft 365 apps and Teams, Microsoft Copilot paid work chat; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Commercial Microsoft Copilot add-on for Word writing examples; general work-chat prompts where the support guide explicitly applies; add_ons=Eligible Microsoft 365 base subscription, Paid Microsoft Copilot add-on; called Microsoft 365 Copilot in some source pages, Source-service credentials/subscriptions and Purview entitlements where required; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Copilot’s prompted translation does not establish preserved page/table layout or a managed corporate glossary.
Word Translator is a separate base-app command; SharePoint/OneDrive glossary translation is separately metered document processing requiring Azure billing and permissions.
No shared translation/glossary/Swiss-language fixture or complete dedicated-engine specification was verified.

document_translation Can whole documents be translated with formatting kept? [partial]: Copilot Chat documents translation of attached or referenced file content. Microsoft separately documents Word Translator creating a formatted translated copy; that is a Word command, not a Copilot Chat formatting guarantee. No DE-to-FR/IT layout fixture was run. Sources: microsoft-copilot:microsoft-copilot:r5-chat-translation, microsoft-copilot:microsoft-copilot:r5-word-translation-boundary.
translation_engine Which engine translates? [unknown]: Unresolved on 2026-10-26. Re-read https://support.microsoft.com/en-us/microsoft-365-copilot/translate-files-into-another-language-in-microsoft-365-copilot-chat and https://word.cloud.microsoft/create/en/blog/how-to-translate-documents-in-word/ . The latter identifies Word Translator as a separate formatting-preserving command and Copilot as a drafting/rewriting route, but does not specify a dedicated Copilot translation engine/model contract. No engine was inferred from the separate Word/SharePoint services.
glossaries Are company glossaries supported? [unknown]: Unresolved on 2026-10-26. Re-read the Copilot translation support page and https://learn.microsoft.com/en-us/microsoft-365/documentprocessing/translation-glossary?view=o365-worldwide plus https://learn.microsoft.com/en-us/microsoft-365/documentprocessing/syntex-azure-billing?view=o365-worldwide . SharePoint supports glossary files in separately metered document processing; a maintained glossary enforced by Copilot Chat/Word prompts or included with a Copilot seat was not established. No glossary fixture was run.
formality_and_variants Can formality and regional variants (de-CH) be set? [partial]: Official Copilot examples accept tone/style/country and region-specific wording instructions, including refining translated Word content. A deterministic de-CH preset, terminology enforcement and dialect-quality result were not established. Sources: microsoft-copilot:microsoft-copilot:r5-chat-translation, microsoft-copilot:microsoft-copilot:r5-word-translation-boundary.
writing_tools Are dedicated rewrite and proofreading tools available? [partial]: The direct support guide documents drafting from prompts and Word paragraph rewriting; work-data-grounded prompts require the commercial Copilot subscription. Sources: microsoft-copilot:ms-writing-r2.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:ms-writing-r2, microsoft-copilot:microsoft-copilot:r5-chat-translation, microsoft-copilot:microsoft-copilot:r5-word-translation-boundary, microsoft-copilot:microsoft-copilot:r5-sharepoint-translation, microsoft-copilot:microsoft-copilot:r5-sharepoint-glossary, microsoft-copilot:microsoft-copilot:r5-sharepoint-metering.

WORK-04 Image generation and editing

Judgment rule: Record available image models, editing (inpainting, reference images), admin control and per-image cost visibility, and licence or usage terms for generated images.

LibreChat

Agent cross-checked Support: partial

Configured Agent image tools generate and edit images; model service rights/costs remain separate.

Limitations

admin_control: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established.
usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement.

image_generation Can users generate images, with which models? [supported]: OpenAI Image Tools and additional documented provider tools attach to an Agent; the current guide defaults OpenAI tools to gpt-image-2.5-flare. Sources: librechat:librechat:images.
image_editing Can users edit uploaded images? [supported]: The image guide documents editing/remixing uploaded images using image IDs and compatible tools. Sources: librechat:librechat:images.
admin_control Can admins restrict image generation? [partial]: Operators control tool credentials/configuration and Agent creation/access permissions. A dedicated per-group image-spend switch was not established. Sources: librechat:librechat:images, librechat:librechat:access.
usage_terms What usage rights apply to output? [unknown]: usage_terms: What usage rights apply to output? Generated-output rights and complete per-image cost visibility were not established as a LibreChat software entitlement.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:images, librechat:librechat:access.

Microsoft Copilot

Agent cross-checked Support: partial

Image generation and an administrator restriction are documented. General output ownership terms apply; editing and image-model-specific rights remain incomplete.

Limitations

Image editing remains unverified.
Administrator image-generation controls are documented; full image-model-specific output rights remain unverified.

image_generation Can users generate images, with which models? [partial]: Create/image generation appears in Chat and paid offerings; the current image-model mapping was not established. Sources: microsoft-copilot:ms-price-us.
image_editing Can users edit uploaded images? [unknown]: Can users edit uploaded images? Unverified after checking Copilot commercial comparison and release notes; current editing, model-specific cost, image policy and output licence terms not fully retrieved.
admin_control Can admins restrict image generation? [supported]: An authorized administrator can allow or prevent supported image generation under Copilot Settings. Availability depends on the tenant licence, enabled features and rollout; group-level behavior was not tested. Sources: microsoft-copilot:microsoft-copilot:r4-image-admin.
usage_terms What usage rights apply to output? [partial]: The commercial Generative AI Product Terms treat output as Customer Data and state Microsoft does not own it. A complete image-model-specific rights or third-party restriction matrix was not verified. Sources: microsoft-copilot:microsoft-copilot:r4-online-service-terms.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:microsoft-copilot:r4-image-admin, microsoft-copilot:microsoft-copilot:r4-online-service-terms.

WORK-05 Voice and meetings

Judgment rule: Record dictation, read-aloud, live voice conversation, meeting transcription and summarisation, supported languages including Swiss German speech, and where audio is processed.

LibreChat

Agent cross-checked Support: partial

LibreChat documents STT, TTS and a hands-free conversation mode that chains them. Real-time speech-to-speech behavior, meeting outcomes and Swiss German recognition remain unverified.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Current self-hosted LibreChat Speech Settings documentation retrieved 2026-10-21; no voice-latency or dialect fixture performed; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Optional configured STT/TTS engines and provider credentials; self-hosted speech services need allowedAddresses; deployment_mode=on-premise; region=Customer-selected app infrastructure; audio processing depends on browser or configured external/self-hosted speech engines, with no universal region verified; os=not specified.

Limitations

Conversation mode is a chain of transcription, text generation and playback; real-time audio-to-audio behavior, interruption and latency were not verified.
Audio location depends on the chosen engine. No meeting or Swiss German fixture was run.

dictation Can users dictate prompts? [supported]: Speech configuration provides STT for audio input. Sources: librechat:librechat:speech.
read_aloud Can answers be read aloud? [supported]: Speech configuration provides TTS for model responses. Sources: librechat:librechat:speech.
voice_conversation Is a live voice mode available? [partial]: speechTab.conversationMode chains STT and TTS for hands-free turns: autoSendText sends the transcript after a configured delay, and automaticPlayback reads a completed response. Microphone recording is initially started by the user. Real-time speech-to-speech, interruption behavior and end-to-end latency were not tested. Sources: librechat:librechat:speech-conversation-r2.
meeting_summaries Are meetings transcribed and summarised? [unknown]: No meeting capture/integration, speaker diarization or meeting-summary fixture was verified in the reviewed speech documentation.
swiss_german_speech Is Swiss German speech recognised? [unknown]: Swiss German recognition and transcript quality were not tested; a language setting does not establish dialect accuracy.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:speech, librechat:librechat:speech-conversation-r2.

Microsoft Copilot

Agent cross-checked Support: partial

Work-account dictation, read-aloud and live voice are documented with availability limits.

Limitations

Unverified parts: meeting_summaries, swiss_german_speech.
Read each atomic answer for its plan, access and feature limits.

dictation Can users dictate prompts? [supported]: Work/school dictation sends speech to Microsoft for transcription without retaining dictation audio. Sources: microsoft-copilot:ms-voice.
read_aloud Can answers be read aloud? [supported]: Read-aloud uses client-side text-to-speech. Sources: microsoft-copilot:ms-voice.
voice_conversation Is a live voice mode available? [partial]: Live voice is documented for work/school accounts, subject to subscription and region; feedback audio is removed after 48 hours. Sources: microsoft-copilot:ms-voice.
meeting_summaries Are meetings transcribed and summarised? [unknown]: Are meetings transcribed and summarised? Unverified after checking Copilot Voice and work-language pages; meeting transcription prerequisites and Swiss German dialect recognition not tested or established.
swiss_german_speech Is Swiss German speech recognised? [unknown]: Is Swiss German speech recognised? Unverified after checking Copilot Voice and work-language pages; meeting transcription prerequisites and Swiss German dialect recognition not tested or established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-voice.

WORK-06 Data analysis and document output

Judgment rule: Record code execution for data analysis, charts, and generation of downloadable Word, Excel, PowerPoint and PDF files. Analyse the fixture Excel and request a PowerPoint summary. Record where code runs and whether files are editable.

LibreChat

Agent cross-checked Support: partial

The separate Code Interpreter runs analysis and produces downloadable files; artifacts provide code/HTML/diagram previews.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separately operated compatible Code Interpreter service, Experimental stateful workspaces only if explicitly configured; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

charts: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run.
office_file_output: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture.
canvas_editing: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established.

data_analysis Can it analyse spreadsheets with executed code? [supported]: Configured Code Interpreter executes programs against uploaded files in its separate sandbox. Sources: librechat:librechat:code.
charts Can it produce charts? [partial]: Code execution and generated-file downloads support chart artifacts, but the shared spreadsheet/chart fixture was not run. Sources: librechat:librechat:code.
office_file_output Can it create Word, Excel or PowerPoint files? [partial]: Generated files are downloadable; editable Word/Excel/PowerPoint fidelity was not established with a fixture. Sources: librechat:librechat:code.
canvas_editing Is there a document or canvas editor for iterating on output? [partial]: Artifacts render React/HTML/Mermaid content and source; a rich Office document editor was not established. Sources: librechat:librechat:artifacts.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:code, librechat:librechat:artifacts.

Microsoft Copilot

Agent cross-checked Support: partial

Python execution and downloadable Office files are documented.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot paid work chat, Copilot in Microsoft 365 apps and Teams; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Paid Microsoft Copilot with code interpreter/eligible Agent Builder agents; generated Word/Excel/PowerPoint files as documented for Chat; add_ons=Eligible Microsoft 365 base subscription, Paid Microsoft Copilot add-on; called Microsoft 365 Copilot in some source pages, Source-service credentials/subscriptions and Purview entitlements where required; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

No analysis entitlement is inferred for every included-Chat client. Scope uses the paid Copilot code path explicitly named by the security architecture.
No spreadsheet/formula or editable-PowerPoint fixture was run. Notebook instruction sharing is not counted as an output canvas.

data_analysis Can it analyse spreadsheets with executed code? [supported]: In the paid Copilot/eligible agent code-interpreter path, LLM-generated Python runs in isolated Azure VMs with no network traffic. Sources: microsoft-copilot:ms-code-r2.
charts Can it produce charts? [supported]: The same paid code-interpreter path can generate data visualizations. Sources: microsoft-copilot:ms-code-r2.
office_file_output Can it create Word, Excel or PowerPoint files? [supported]: Chat's Word/Excel/PowerPoint agents generate files: Word/Excel download; PowerPoint uses OneDrive when available, otherwise download. Sources: microsoft-copilot:ms-chat-privacy-r2.
canvas_editing Is there a document or canvas editor for iterating on output? [unknown]: Notebook instruction editing does not establish an editor for generated output. Output-canvas behavior remains unverified after checking code-interpreter, file-generation and notebook instruction documentation.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-code-r2, microsoft-copilot:ms-chat-privacy-r2.

WORK-07 Sharing and team spaces

Judgment rule: Record chat sharing (link, user, group), shared projects or team spaces, channels or group chat with AI, and commenting. Test sharing a chat with a colleague in another group and record what the recipient sees, including knowledge they lack access to.

LibreChat

Agent cross-checked Support: partial

Shared chat links publish transcript snapshots and optional files. Projects are personal, and shared source permission boundaries need care.

Limitations

group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy.
share_permission_boundary: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run.

share_chats Can chats be shared inside the organisation? [supported]: Authenticated shared links are supported, with optional public viewing; public unauthenticated access is off by default. Sources: librechat:librechat:share.
team_spaces Are shared projects or workspaces available? [unsupported]: Projects specifically cannot be shared or transferred and are personal to the creator. Shared Agents/resources are a separate capability. Sources: librechat:librechat:projects.
group_chat Can several people chat together with the AI? [unknown]: group_chat: Can several people chat together with the AI? Simultaneous multi-person AI group chat was not established from Projects and shareable-link documentation; link continuation creates a separate personal copy.
share_permission_boundary Does sharing respect the recipient's access to sources? [partial]: Published file snapshots are served independently of the owner’s live file ACL. Sharing grants access to the published copy, not continuing source-system authorization; no restricted-source fixture was run. Sources: librechat:librechat:share.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:share, librechat:librechat:projects.

Microsoft Copilot

Agent cross-checked Support: partial

Shared notebooks and agents are documented; chat-sharing boundaries remain untested.

Limitations

Unverified parts: share_chats, group_chat, share_permission_boundary.

share_chats Can chats be shared inside the organisation? [unknown]: Can chats be shared inside the organisation? Unverified after checking notebook sharing and Agent Builder limitations; no cross-group chat-sharing or group-chat test.
team_spaces Are shared projects or workspaces available? [supported]: Users can collaborate on shared notebooks and share agents. Sources: microsoft-copilot:ms-notebook-instructions, microsoft-copilot:ms-agents.
group_chat Can several people chat together with the AI? [unknown]: Can several people chat together with the AI? Unverified after checking notebook sharing and Agent Builder limitations; no cross-group chat-sharing or group-chat test.
share_permission_boundary Does sharing respect the recipient's access to sources? [unknown]: Does sharing respect the recipient's access to sources? Unverified after checking notebook sharing and Agent Builder limitations; no cross-group chat-sharing or group-chat test.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-notebook-instructions, microsoft-copilot:ms-agents.

WORK-08 Interface languages and accessibility

Judgment rule: Record UI languages, focusing on German, French, Italian and English, with translation quality observed (complete, partial, machine-translated). Record response language handling and WCAG conformance statements.

LibreChat

Agent cross-checked Support: partial

English, German, French and Italian UI resources are registered in the pinned client; quality and accessibility conformance were not evaluated.

Limitations

dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.

ui_languages Which UI languages are offered? [supported]: The client i18n implementation registers en, de, fr and it among community-maintained translations. Sources: librechat:librechat:i18n-pin.
dach_language_quality Are German, French and Italian UIs complete and natural? [unknown]: dach_language_quality: Are German, French and Italian UIs complete and natural? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
accessibility_statement Is there a WCAG conformance statement? [unknown]: accessibility_statement: Is there a WCAG conformance statement? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.
admin_ui_languages Is the admin interface available in German? [unknown]: admin_ui_languages: Is the admin interface available in German? No complete DE/FR/IT walkthrough, German separate-admin-panel coverage test or WCAG conformance statement/report was verified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:i18n-pin.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft lists the target European languages; naturalness and conformance remain unchecked.

Limitations

Localization availability is documented; linguistic quality was not observed.

ui_languages Which UI languages are offered? [supported]: Microsoft lists English, German, French and Italian among supported work languages and states localization. Sources: microsoft-copilot:ms-language.
dach_language_quality Are German, French and Italian UIs complete and natural? [unknown]: Are German, French and Italian UIs complete and natural? Unverified after checking supported-language page; no localized UI inspection, admin-language pass or product-specific WCAG report.
accessibility_statement Is there a WCAG conformance statement? [unknown]: Is there a WCAG conformance statement? Unverified after checking supported-language page; no localized UI inspection, admin-language pass or product-specific WCAG report.
admin_ui_languages Is the admin interface available in German? [unknown]: Is the admin interface available in German? Unverified after checking supported-language page; no localized UI inspection, admin-language pass or product-specific WCAG report.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-language.

Administration and governance

ADM-01 Single sign-on and authentication

Judgment rule: Record SAML, OIDC, Microsoft Entra ID, Google, LDAP, MFA enforcement, conditional-access compatibility, domain verification and plan restrictions. Test one SSO login on a trial where possible.

LibreChat

Agent cross-checked Support: partial

Self-hosted authentication supports OAuth/OIDC, SAML and LDAP; local/LDAP TOTP can be enforced.

Limitations

conditional_access: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested.
domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim.

sso_protocols Which SSO protocols and identity providers work? [supported]: OIDC/OAuth providers include Entra, Google, Keycloak and Auth0; SAML and LDAP are documented separately. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth.
sso_plan Which plan includes SSO? [supported]: The authentication configuration belongs to the MIT self-hosted project, with no separate SSO licence tariff. Sources: librechat:librechat:license, librechat:librechat:auth.
mfa Can MFA be enforced? [supported]: ENFORCE_TWO_FACTOR_AUTHENTICATION requires local/LDAP enrollment and prevents disabling it; federated accounts depend on IdP MFA. Sources: librechat:librechat:auth.
conditional_access Do Entra conditional-access policies apply? [partial]: Entra authentication and token reuse are documented, but an actual conditional-access/device-policy login was not tested. Sources: librechat:librechat:entra.
domain_capture Can the company claim its email domain? [unknown]: domain_capture: Can the company claim its email domain? Registration/domain filters were not established as a tenant-wide company-domain ownership claim.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:openid, librechat:librechat:saml, librechat:librechat:auth, librechat:librechat:license, librechat:librechat:entra.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft 365 identity, MFA and conditional-access setup are documented.

Limitations

Unverified parts: domain_capture.
Read each atomic answer for its plan, access and feature limits.

sso_protocols Which SSO protocols and identity providers work? [partial]: Copilot uses Microsoft 365/Entra work accounts; exact application protocol and direct LDAP alternatives were not verified. Sources: microsoft-copilot:ms-price-us.
sso_plan Which plan includes SSO? [supported]: Chat requires an eligible M365 account; paid access adds a Copilot licence. Sources: microsoft-copilot:ms-price-us.
mfa Can MFA be enforced? [supported]: Deployment guidance documents enforcing MFA through Entra policies. Sources: microsoft-copilot:ms-setup.
conditional_access Do Entra conditional-access policies apply? [partial]: Setup guidance documents conditional access, including SharePoint tenant-level policies. Sources: microsoft-copilot:ms-setup.
domain_capture Can the company claim its email domain? [unknown]: Can the company claim its email domain? Unverified after checking Copilot licence and deployment guidance; no trial SSO login or domain-claim test.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-setup.

ADM-02 User provisioning and lifecycle

Judgment rule: Record SCIM, just-in-time provisioning, group sync from the identity provider, deprovisioning effects (chats, assistants, knowledge ownership transfer) and licence assignment. Deprovision a test user and record what happens to their content.

LibreChat

Agent cross-checked Support: partial

Entra group synchronization and federated account creation are documented; SCIM and leaver content transfer remain unknown.

Limitations

scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run.
deprovisioning: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested.
seat_assignment: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source.

scim Is SCIM provisioning supported? [unknown]: scim: Is SCIM provisioning supported? SCIM was not established in the authentication/access docs or pinned repository path review. No two-user deprovisioning fixture was run.
group_sync Are identity-provider groups synced? [supported]: With Entra OIDC token reuse, Graph groups sync at login; resource ACL principal membership has a documented cache. Sources: librechat:librechat:access, librechat:librechat:entra.
jit_provisioning Are users created at first login? [supported]: Federated login creates accounts according to the authentication configuration; OpenID/SAML registration cannot be independently disabled. Sources: librechat:librechat:auth.
deprovisioning What happens to a removed user's data and shared assets? [partial]: The docs provide user deletion scripts, but content ownership transfer and revocation behavior were not fixture-tested. Sources: librechat:librechat:auth.
seat_assignment Can admins assign and reclaim seats? [partial]: Operators manage accounts/roles under an MIT licence; there is no per-seat licence entitlement in the scoped source. Sources: librechat:librechat:auth, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:entra, librechat:librechat:auth, librechat:librechat:license.

Microsoft Copilot

Agent cross-checked Support: partial

Seat assignment is tenant-managed; provisioning and content-transfer details remain open.

Limitations

Unverified parts: scim, group_sync, jit_provisioning, deprovisioning.

scim Is SCIM provisioning supported? [unknown]: Is SCIM provisioning supported? Unverified after checking Microsoft Copilot setup; SCIM/JIT, group provisioning and leaver asset transfer were not separately documented or tested.
group_sync Are identity-provider groups synced? [unknown]: Are identity-provider groups synced? Unverified after checking Microsoft Copilot setup; SCIM/JIT, group provisioning and leaver asset transfer were not separately documented or tested.
jit_provisioning Are users created at first login? [unknown]: Are users created at first login? Unverified after checking Microsoft Copilot setup; SCIM/JIT, group provisioning and leaver asset transfer were not separately documented or tested.
deprovisioning What happens to a removed user's data and shared assets? [unknown]: What happens to a removed user's data and shared assets? Unverified after checking Microsoft Copilot setup; SCIM/JIT, group provisioning and leaver asset transfer were not separately documented or tested.
seat_assignment Can admins assign and reclaim seats? [supported]: M365 administrators assign purchased Copilot licences to users. Sources: microsoft-copilot:ms-setup.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-setup.

ADM-03 Roles, groups and feature permissions

Judgment rule: Record admin roles, delegated admins, groups, per-feature permissions (web search, image generation, connectors, file upload, agents), separation of subsidiaries or departments, and enforcement. Test one disabled feature for one group.

LibreChat

Agent cross-checked Support: partial

Role permissions, resource ACLs and system grants support granular governance; the separate management UI remains preview.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, Separately deployed LibreChat Admin Panel preview; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Separate Admin Panel preview for GUI management; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

Separate admin management UI is preview; the core authorization model is documented as available.
No two-group disabled-feature fixture was run.

admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: ADMIN/USER and custom roles exist; capability grants can delegate selected administrative functions without full admin. Sources: librechat:librechat:access.
groups Can permissions be set per group? [supported]: Local and Entra groups can receive ACLs, system grants and configuration overrides. Sources: librechat:librechat:access, librechat:librechat:admin.
feature_toggles Which features can be switched on or off per group? [supported]: Permissions include Agents, MCP, prompts, memory, search, file search/citations and code execution. Sources: librechat:librechat:access.
multi_entity Can subsidiaries or departments be separated within one contract? [partial]: Tenant-scoped API queries and group/configuration boundaries are documented. A commercial multi-entity contract and tested tenant isolation were not established. Sources: librechat:librechat:insights, librechat:librechat:access.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:access, librechat:librechat:admin, librechat:librechat:insights.

Microsoft Copilot

Agent cross-checked Support: partial

Administrative roles and selected group-targeted controls are documented.

Limitations

No disabled-feature test with two groups was performed.

admin_roles Which admin roles exist, and can admin rights be delegated? [supported]: M365, SharePoint, Purview and billing functions use distinct administrator roles. Sources: microsoft-copilot:ms-setup, microsoft-copilot:ms-cost-setup.
groups Can permissions be set per group? [supported]: Web-search and Anthropic settings can target groups. Sources: microsoft-copilot:ms-manage, microsoft-copilot:ms-anthropic.
feature_toggles Which features can be switched on or off per group? [partial]: Admins control web search and Agent Builder; Anthropic access has separate user/group controls. Sources: microsoft-copilot:ms-manage, microsoft-copilot:ms-builder, microsoft-copilot:ms-anthropic.
multi_entity Can subsidiaries or departments be separated within one contract? [unknown]: Can subsidiaries or departments be separated within one contract? Unverified after checking Copilot admin controls; complete feature-by-group and subsidiary isolation behavior not tested.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-setup, microsoft-copilot:ms-cost-setup, microsoft-copilot:ms-manage, microsoft-copilot:ms-anthropic, microsoft-copilot:ms-builder.

ADM-04 Usage and adoption analytics

Judgment rule: Record dashboards for active users, usage by feature, model, group and assistant, export, and privacy controls (aggregation, pseudonymisation, works-council-friendly settings). Distinguish aggregate adoption metrics from per-person monitoring.

LibreChat

Agent cross-checked Support: partial

Optional Insights reports identifiable activity; token transactions and optional tracing are separate sources of usage detail.

Limitations

breakdowns: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established.
export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified.
privacy_modes: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established.

adoption_dashboard Is there an adoption dashboard? [supported]: Opt-in Insights reports conversations, unique users, messages, tokens, top users and recent conversations. Sources: librechat:librechat:insights.
breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Insights supports Agent filtering and user activity; recorded token/context cost details are per model/endpoint. Complete group/feature/assistant exports were not established. Sources: librechat:librechat:insights, librechat:librechat:tokens.
export Can usage data be exported? [unknown]: export: Can usage data be exported? A documented complete admin analytics export and group/cost-centre dataset were not verified.
privacy_modes Can per-person reporting be limited or pseudonymised? [partial]: Insights is off unless enabled and is capability-gated; it can display names, emails and first-message content. Pseudonymized reporting was not established. Sources: librechat:librechat:insights.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:insights, librechat:librechat:tokens.

Microsoft Copilot

Agent cross-checked Support: partial

Chat and paid usage reports are separate and have privacy controls.

Limitations

Read each atomic answer for its plan, access and feature limits.

adoption_dashboard Is there an adoption dashboard? [supported]: Microsoft publishes distinct paid Copilot and unlicensed Chat usage dashboards. Sources: microsoft-copilot:ms-usage, microsoft-copilot:ms-chat-usage.
breakdowns Can usage be broken down by group, model, feature and assistant? [partial]: Reports include application entry points and user activity; complete model/group/assistant breakdowns were not verified. Sources: microsoft-copilot:ms-usage, microsoft-copilot:ms-chat-usage.
export Can usage data be exported? [supported]: The Chat report exports all reported user usage as CSV. Sources: microsoft-copilot:ms-chat-usage.
privacy_modes Can per-person reporting be limited or pseudonymised? [supported]: Identifying user, group and site fields are hidden by default; administrators can change report settings. Sources: microsoft-copilot:ms-usage.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-usage, microsoft-copilot:ms-chat-usage.

ADM-05 Spend controls and cost allocation

Judgment rule: Record cost visibility per user, group and cost centre, budgets and their behaviour (alert, block, downgrade model), pooled credits, and chargeback exports. Test a small budget on a trial where possible. Distinguish billed amounts, estimates and unavailable amounts.

LibreChat

Agent cross-checked Support: partial

Optional token-credit balances block admission when insufficient; credit estimates differ from actual cloud invoices.

Limitations

cost_visibility: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing.
budgets: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established.
chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established.

cost_visibility Can admins see cost or consumption per user and group? [partial]: Token transactions and configured token prices support per-user/model estimates. Insights explicitly reports activity rather than monetary billing. Sources: librechat:librechat:tokens, librechat:librechat:insights.
budgets Can budgets be set per user or group? [partial]: Optional per-user start balances and automatic refills are documented. Group/cost-centre pooled budgets were not established. Sources: librechat:librechat:balance.
budget_enforcement Does reaching a budget alert, block or downgrade? [supported]: Pinned balance middleware reserves estimated token cost and throws an error if credits cannot be reserved; no low-budget trial was run. Sources: librechat:librechat:balance-pin.
chargeback Can costs be exported per cost centre? [unknown]: chargeback: Can costs be exported per cost centre? Cost-centre chargeback exports and reconciliation to actual vendor invoices were not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:tokens, librechat:librechat:insights, librechat:librechat:balance, librechat:librechat:balance-pin.

Microsoft Copilot

Agent cross-checked Support: partial

Metered-service cost management supports limits; exact stop semantics need verification.

Limitations

Prepaid-credit exhaustion alone can continue into PAYG; it is not itself a hard budget.

cost_visibility Can admins see cost or consumption per user and group? [partial]: The cost dashboard shows credit consumption and billing configuration; complete cost-centre mapping was not verified. Sources: microsoft-copilot:ms-cost-setup.
budgets Can budgets be set per user or group? [supported]: Policies support monthly spending limits and optional per-user limits. Sources: microsoft-copilot:ms-cost-setup.
budget_enforcement Does reaching a budget alert, block or downgrade? [partial]: The setup describes limits on monthly credit spend, but overshoot, timing and enforcement were not tested. Sources: microsoft-copilot:ms-cost-setup.
chargeback Can costs be exported per cost centre? [unknown]: Can costs be exported per cost centre? Unverified after checking Copilot Credits cost management and rate documentation; chargeback exports and enforced-stop timing not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-cost-setup.

ADM-06 Audit logs and compliance export

Judgment rule: Record which events are logged (logins, admin changes, prompts, responses, file access, connector queries), retention, export or SIEM streaming, and eDiscovery/legal hold. Use the word audit only with a defined retention and integrity model.

LibreChat

Agent cross-checked Support: partial

Operational logs and persisted chats are available; a complete audit retention/integrity or eDiscovery system was not verified.

Limitations

admin_events: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established.
content_logging: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive.
siem_export: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified.
ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified.
log_retention: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks.

admin_events Are admin and security events logged? [partial]: Backend logs capture errors/debug activity and can include operational/security actions. A complete immutable admin-event schema was not established. Sources: librechat:librechat:logging.
content_logging Can prompts and answers be retained for compliance, and is it configurable? [partial]: Chats are persisted in MongoDB subject to retention settings; external tracing is optional. This is not a verified compliance archive. Sources: librechat:librechat:retention, librechat:librechat:compose-pin.
siem_export Can logs stream to a SIEM or be exported? [partial]: Operators can feed log files to external systems such as ELK. A native managed SIEM stream and integrity guarantee were not verified. Sources: librechat:librechat:logging.
ediscovery Are eDiscovery and legal hold supported? [unknown]: ediscovery: Are eDiscovery and legal hold supported? No eDiscovery/legal hold, tamper-evident archive or complete prompt/file/connector event coverage was verified.
log_retention How long are logs kept? [partial]: The logging guide describes 14-day rotation. Rotation is not evidence of an enforced legal retention or deletion guarantee across external sinks. Sources: librechat:librechat:logging.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:retention, librechat:librechat:compose-pin.

Microsoft Copilot

Agent cross-checked Support: partial

Purview provides interaction records and compliance retention, with licence-dependent policies.

Limitations

Compliance copies differ from the visible chat history. No export or hold test was run.

admin_events Are admin and security events logged? [supported]: With auditing enabled, Purview logs Copilot admin changes and user resource/agent metadata. Sources: microsoft-copilot:ms-audit.
content_logging Can prompts and answers be retained for compliance, and is it configurable? [supported]: Prompts/responses are retained in Exchange-backed compliance copies; administrators can apply retention. Sources: microsoft-copilot:ms-retention.
siem_export Can logs stream to a SIEM or be exported? [supported]: Purview supports export of Copilot audit events. Microsoft documents EXO CSV export and Office 365 Management Activity API streaming of CopilotInteraction events to a SIEM; this does not imply full prompt/response content in audit metadata. Sources: microsoft-copilot:microsoft-copilot:r4-audit-export, microsoft-copilot:microsoft-copilot:r4-audit-api.
ediscovery Are eDiscovery and legal hold supported? [supported]: Hidden interaction copies are searchable through eDiscovery and remain subject to holds. Sources: microsoft-copilot:ms-retention.
log_retention How long are logs kept? [partial]: Audit Standard and Premium have distinct retention entitlements; a product-specific integrity and exact retention configuration was not verified. Sources: microsoft-copilot:ms-audit-standard.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:ms-audit, microsoft-copilot:ms-retention, microsoft-copilot:ms-audit-standard, microsoft-copilot:microsoft-copilot:r4-audit-export, microsoft-copilot:microsoft-copilot:r4-audit-api.

ADM-07 Data loss prevention and personal data

Judgment rule: Record detection and handling of personal and confidential data before it reaches a model: redaction, masking, blocking, warning. Record integration with Purview, Netskope or similar, and whether filtering runs locally or at a third party. Send a fixture prompt with a Swiss AHV number and IBAN and record the outcome.

LibreChat

Agent cross-checked Support: partial

Optional server-side content filters support configured pattern detection, blocking and auditing, plus narrowly scoped Agent text redaction. External DLP integration and fixture accuracy remain unknown.

Availability: source-only · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Development source a378657583567310c841d652b0f6b00c83e2bd6b; current Latest (dev) documentation; limited redaction announced in config v1.3.18 on 2026-10-22; plan=Customer-operated LibreChat; optional base-YAML content policies, disabled unless configured; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

Development-source finding; no running instance or AHV/IBAN fixture.
Filtering is opt-in and limited to configured sources/fields. Default patterns cover credential shapes, not every PII class.
Redaction applies only to eligible fresh Agent text; encrypted originals remain stored.
A dedicated external DLP integration remains unverified.

pii_detection Is personal data detected in prompts and files? [partial]: Configured source-aware policies can inspect selected prompt fields and file names/extracted text/transcripts. Built-in starter rules match credentials; admins must supply additional personal-data patterns. Opaque files may be allowed by default or explicitly blocked. AHV/IBAN and confidential-file detection accuracy were not tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware.
pii_action Is it redacted, masked, blocked or only warned? [partial]: Configured matches can block or audit. Redaction transforms only fresh, text-only interactive Agent submissions carrying clientRequestId and a valid CREDS_KEY; edits, resumes, files, quotes and other endpoints retain blocking checks. Original text is encrypted and unindexed, rather than discarded. No running deployment was tested. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware.
custom_patterns Can admins add custom patterns or terms? [supported]: Operators can add labelled custom RE2JS regular expressions in base librechat.yaml, with optional categories. Database/role/group/user overrides cannot modify the policy; all replicas must load matching configuration. Invalid rules are rejected on configuration load. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-patterns, librechat:librechat:r4-filter-middleware.
dlp_integration Does it integrate with an existing DLP product? [unknown]: No first-party Purview/Netskope or other external DLP connector was established from the content-filter guide, current public repository tree and targeted official-site search. Configurable local patterns are not evidence of an external enterprise DLP integration.
filter_location Where does filtering run? [supported]: Inspected content-filter middleware and rule evaluation run in the customer-operated LibreChat API backend. Optional extraction/OCR and inference providers remain separate data flows; no named deployment region or traffic path was tested. Sources: librechat:librechat:r4-pii-runtime, librechat:librechat:r4-filter-middleware.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: librechat:librechat:r4-content-filter, librechat:librechat:r4-pii-runtime, librechat:librechat:r4-patterns, librechat:librechat:r4-private-submission, librechat:librechat:r4-filter-middleware, librechat:librechat:r4-config-1318.

Microsoft Copilot

Agent cross-checked Support: partial

Purview can block sensitive prompts when configured; its default policy simulates.

Limitations

No Swiss AHV or IBAN test was performed.

pii_detection Is personal data detected in prompts and files? [supported]: Purview DLP can match selected sensitive information types in prompts. Sources: microsoft-copilot:ms-dlp.
pii_action Is it redacted, masked, blocked or only warned? [supported]: Configured policies prevent prompt processing; the default policy is simulation/alert mode. Sources: microsoft-copilot:ms-dlp, microsoft-copilot:ms-dlp-default.
custom_patterns Can admins add custom patterns or terms? [supported]: The Copilot DLP location supports custom sensitive-information types for prompt blocking. This control is in preview and subject to tenant rollout and licensing; the location does not scan files uploaded directly in prompts. No AHV/IBAN fixture was run. Sources: microsoft-copilot:microsoft-copilot:r4-custom-dlp-types.
dlp_integration Does it integrate with an existing DLP product? [partial]: Microsoft Purview is the documented integration; base subscription entitlements determine available controls. Sources: microsoft-copilot:ms-dlp, microsoft-copilot:ms-setup.
filter_location Where does filtering run? [unknown]: Where does filtering run? Unverified after checking Purview DLP documentation; custom AHV/IBAN patterns, filtering geography and fixture behavior unverified.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:ms-dlp, microsoft-copilot:ms-dlp-default, microsoft-copilot:ms-setup, microsoft-copilot:microsoft-copilot:r4-custom-dlp-types.

ADM-08 AI policy and guardrails

Judgment rule: Record organisation-wide system instructions, acceptable-use notices and acknowledgement, content filters, topic restrictions, AI-output labelling, and admin visibility of policy violations. Separate enforced policy from instructions the model is expected to follow.

LibreChat

Agent cross-checked Support: partial

Operators can configure prompts and usage terms; abuse moderation is distinct from semantic content-policy enforcement.

Limitations

org_instructions: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement.
content_filters: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established.
violation_reporting: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established.

org_instructions Can admins set organisation-wide instructions? [partial]: Enforced model-spec presets and Agent instructions can guide behavior; model-followed instructions are not guaranteed policy enforcement. Sources: librechat:librechat:modelspec, librechat:librechat:agents.
usage_notice Can users be required to accept a usage policy? [supported]: Interface configuration includes custom terms of service and acceptance settings. Sources: librechat:librechat:interface.
content_filters Are content filters configurable? [partial]: Automated moderation scores rate/authentication/message abuse and can ban users. Semantic topic or PII policy coverage was not established. Sources: librechat:librechat:mod.
violation_reporting Are policy hits visible to admins? [partial]: Abuse scoring is documented, but a complete organization content-policy violation dashboard and reporting fixture were not established. Sources: librechat:librechat:mod.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:modelspec, librechat:librechat:agents, librechat:librechat:interface, librechat:librechat:mod.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft documents safety controls and policy metadata; organization-wide instruction enforcement remains unverified.

Limitations

Unverified parts: org_instructions, usage_notice.
Read each atomic answer for its plan, access and feature limits.

org_instructions Can admins set organisation-wide instructions? [unknown]: Can admins set organisation-wide instructions? Unverified after checking Copilot privacy and audit schemas; organization-wide instructions and mandatory AUP acknowledgement not established.
usage_notice Can users be required to accept a usage policy? [unknown]: Can users be required to accept a usage policy? Unverified after checking Copilot privacy and audit schemas; organization-wide instructions and mandatory AUP acknowledgement not established.
content_filters Are content filters configurable? [partial]: Copilot documents harmful-content and prompt-injection protections; customer configurability was not established. Sources: microsoft-copilot:ms-privacy.
violation_reporting Are policy hits visible to admins? [partial]: Audit resource metadata can include policy restrictions and prompt-injection detection; complete violation coverage was not established. Sources: microsoft-copilot:ms-audit.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-privacy, microsoft-copilot:ms-audit.

Data protection and sovereignty

DATA-01 Hosting location and data residency

Judgment rule: Record country or region separately for chat storage, files and indexes, model inference, backups, logs and telemetry, and support access. Name the cloud provider. Record whether residency is default, a paid option or plan-dependent. "EU data boundary" programmes are recorded with their documented exceptions.

LibreChat

Agent cross-checked Support: partial

Customer operators choose storage and service locations; external model, OCR, search and code services need separate residency decisions.

Limitations

backups_logs_region: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited.
support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment.
swiss_hosting: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established.

storage_region Where are chats, files and indexes stored? [supported]: The reference self-hosted stack keeps application data in configured MongoDB/files and retrieval data in PGVector. Its country is chosen by the deployer. Sources: librechat:librechat:compose-pin, librechat:librechat:remote.
inference_region Where do model calls run, per provider? [supported]: Customer-selected cloud endpoints/regions or local endpoints determine inference; hosting LibreChat in Switzerland does not place every external model there. Sources: librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex.
backups_logs_region Where are backups, logs and telemetry? [partial]: Logs and mounted data reside in the configured deployment; backup, telemetry and optional tracing geographies depend on operator choices and were not audited. Sources: librechat:librechat:logging, librechat:librechat:compose-pin.
support_access_region From where can vendor staff access data? [unknown]: support_access_region: From where can vendor staff access data? No vendor or integrator support-access country restriction was reviewed for this customer-operated deployment.
swiss_hosting Is Swiss hosting available? [partial]: A customer may run the software on Swiss infrastructure; no bundled Swiss managed inference/support commitment was established. Sources: librechat:librechat:remote, librechat:librechat:license.
residency_plan Which plan or option provides residency? [supported]: Customer-controlled placement is a self-hosted deployment property, not a separately priced residency licence. Sources: librechat:librechat:remote, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:custom, librechat:librechat:bedrock, librechat:librechat:vertex, librechat:librechat:logging, librechat:librechat:license.

Microsoft Copilot

Agent cross-checked Support: partial

EU/EFTA commitments have separate model, web-search and operational exceptions.

Limitations

Bing web queries are outside EUDB. Anthropic opt-in changes the model-processing scope. No sovereign-cloud claims are made.

storage_region Where are chats, files and indexes stored? [partial]: Microsoft 365 tenant commitments govern interaction storage and OneDrive files; EUDB covers qualifying EU/EFTA configurations, not a universal Swiss-only deployment. Sources: microsoft-copilot:ms-chat-privacy, microsoft-copilot:ms-eudb.
inference_region Where do model calls run, per provider? [partial]: EU traffic has EUDB safeguards; optional Anthropic is excluded from EUDB and in-country processing commitments. Sources: microsoft-copilot:ms-privacy, microsoft-copilot:ms-anthropic.
backups_logs_region Where are backups, logs and telemetry? [partial]: EUDB includes pseudonymized personal system logs subject to limited-transfer exceptions; a separate backup/telemetry country map was not retrieved. Sources: microsoft-copilot:ms-eudb.
support_access_region From where can vendor staff access data? [partial]: EUDB professional-services data is committed at rest; operational transfers remain possible. This does not prove EU-only staff access. Sources: microsoft-copilot:ms-eudb.
swiss_hosting Is Swiss hosting available? [unknown]: Is Swiss hosting available? Unverified after checking Copilot privacy, EUDB and residency documentation; no comprehensive Swiss storage/inference/support matrix.
residency_plan Which plan or option provides residency? [partial]: Chat and paid Copilot use M365 commitments; model and service-specific exceptions must be applied separately. Sources: microsoft-copilot:ms-edp, microsoft-copilot:ms-anthropic.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-chat-privacy, microsoft-copilot:ms-eudb, microsoft-copilot:ms-privacy, microsoft-copilot:ms-anthropic, microsoft-copilot:ms-edp.

DATA-02 Deployment options

Judgment rule: Record multi-tenant SaaS, dedicated single-tenant instance, deployment in the customer's cloud account, on-premise and air-gapped as separate options with plan and availability. Record which features are missing in each mode, who operates it, and the documented seat or contract threshold for each mode, which can differ from the enterprise plan threshold (e.g. dedicated SaaS from 2,000 seats, own cloud from 5,000). A local-network connector or gateway that reaches on-prem data from a vendor-hosted platform is KNOW-03, not on-premise deployment.

LibreChat

Agent cross-checked Support: partial

The project documents local and customer-cloud installs. A free public demo is separate from a production managed service.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server, LibreChat public evaluation demo; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected infrastructure; model, OCR, search, observability and support services separately scoped; os=not specified.

Limitations

multi_tenant_saas: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence.
dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established.
air_gapped: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified.
mode_feature_gaps: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix.

multi_tenant_saas Is a shared SaaS offered? [partial]: The project operates a free public evaluation Demo, not a reviewed production business SaaS offer. Its terms permit data cleanups and disclaim persistence. Sources: librechat:librechat:demo, librechat:librechat:firstchat.
dedicated_instance Is a dedicated single-tenant instance offered, from what size? [unknown]: dedicated_instance: Is a dedicated single-tenant instance offered, from what size? A vendor-operated dedicated production service and its contractual size floor were not established.
customer_cloud Can it run in the customer's own cloud account, from what size? [supported]: Remote hosting documentation describes customer-selected servers/cloud hosting without a software seat minimum. Sources: librechat:librechat:remote, librechat:librechat:license.
on_premise Can the whole platform run on customer infrastructure, from what size? [supported]: Docker/npm installation can run the application and dependencies on customer infrastructure. Sources: librechat:librechat:local, librechat:librechat:compose-pin.
air_gapped Can it run without internet access? [partial]: Local chat/embedding routes exist, but a complete disconnected installation and its full dependency behavior were not verified. Sources: librechat:librechat:custom, librechat:librechat:ragcfg.
mode_feature_gaps Which features are missing outside SaaS? [partial]: External APIs, OCR/search services and separate code runtimes need their own availability/networking; there is no verified SaaS/on-prem feature-parity matrix. Sources: librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:demo, librechat:librechat:firstchat, librechat:librechat:remote, librechat:librechat:license, librechat:librechat:local, librechat:librechat:compose-pin, librechat:librechat:custom, librechat:librechat:ragcfg, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:code.

Microsoft Copilot

Agent cross-checked Support: partial

The researched offering is Microsoft-operated tenant SaaS; other deployment contracts remain unverified.

Limitations

Unverified parts: dedicated_instance, customer_cloud, on_premise, air_gapped, mode_feature_gaps.

multi_tenant_saas Is a shared SaaS offered? [supported]: Enterprise protection documents isolated customer tenants in Microsoft 365. Sources: microsoft-copilot:ms-edp.
dedicated_instance Is a dedicated single-tenant instance offered, from what size? [unknown]: Is a dedicated single-tenant instance offered, from what size? Unverified after checking Microsoft Copilot commercial plans and architecture; dedicated-instance, customer-cloud, full on-premises and air-gapped offerings and thresholds not established.
customer_cloud Can it run in the customer's own cloud account, from what size? [unknown]: Can it run in the customer's own cloud account, from what size? Unverified after checking Microsoft Copilot commercial plans and architecture; dedicated-instance, customer-cloud, full on-premises and air-gapped offerings and thresholds not established.
on_premise Can the whole platform run on customer infrastructure, from what size? [unknown]: Can the whole platform run on customer infrastructure, from what size? Unverified after checking Microsoft Copilot commercial plans and architecture; dedicated-instance, customer-cloud, full on-premises and air-gapped offerings and thresholds not established.
air_gapped Can it run without internet access? [unknown]: Can it run without internet access? Unverified after checking Microsoft Copilot commercial plans and architecture; dedicated-instance, customer-cloud, full on-premises and air-gapped offerings and thresholds not established.
mode_feature_gaps Which features are missing outside SaaS? [unknown]: Which features are missing outside SaaS? Unverified after checking Microsoft Copilot commercial plans and architecture; dedicated-instance, customer-cloud, full on-premises and air-gapped offerings and thresholds not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-edp.

DATA-03 Training use and provider retention

Judgment rule: Record whether customer content trains vendor or provider models, by plan and default; zero-data-retention arrangements with model providers; abuse-monitoring retention and human review; and the model provider's terms that apply. A "no training" claim on a marketing page is `vendor-claimed` until the contract or DPA says so.

LibreChat

Agent cross-checked Support: partial

The customer configures model contracts and data paths; a universal no-training or provider-retention promise was not established.

Limitations

vendor_training: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service.
provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.

vendor_training Does the vendor train on customer content? [partial]: The self-hosted application stores data in the customer’s configured stack; this architecture is not a contractual promise covering every optional external service. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat.
provider_training Do model providers train on it under this product's contracts? [unknown]: provider_training: Do model providers train on it under this product's contracts? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [unknown]: provider_retention: How long do model providers keep prompts, including for abuse monitoring? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
zero_retention Is zero data retention available, and on which plan? [unknown]: zero_retention: Is zero data retention available, and on which plan? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.
human_review Can provider staff review content? [unknown]: human_review: Can provider staff review content? No specific customer provider agreement, abuse retention/human-review period or zero-retention entitlement was reviewed. Website and Demo privacy policies do not govern arbitrary self-hosted providers.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:compose-pin, librechat:librechat:firstchat.

Microsoft Copilot

Agent cross-checked Support: partial

No-training assertions and provider exceptions are recorded separately from customer retention.

Limitations

No-training statements remain vendor assertions pending direct contract verification. Stored tenant chat history is distinct from provider retention.

vendor_training Does the vendor train on customer content? [partial]: Microsoft states commercial prompts, responses and Graph data do not train foundation models; the underlying DPA text was not inspected. Sources: microsoft-copilot:ms-no-training.
provider_training Do model providers train on it under this product's contracts? [partial]: Microsoft makes the same foundation-model statement; separate Data Retention model terms require their own review. Sources: microsoft-copilot:ms-no-training, microsoft-copilot:ms-anthropic.
provider_retention How long do model providers keep prompts, including for abuse monitoring? [partial]: Some Anthropic models explicitly retain data under separate Anthropic terms; ordinary eligible subprocessor models are described differently. No universal retention period is established. Sources: microsoft-copilot:ms-anthropic.
zero_retention Is zero data retention available, and on which plan? [partial]: Eligible Anthropic subprocessor offerings are described as not retaining customer content; this is not zero retention for M365 interactions. Sources: microsoft-copilot:ms-anthropic.
human_review Can provider staff review content? [partial]: Copilot opts out of Azure OpenAI abuse-monitoring human review; Anthropic illegal-content safeguards are separate. Sources: microsoft-copilot:ms-no-training, microsoft-copilot:ms-anthropic.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-no-training, microsoft-copilot:ms-anthropic.

DATA-04 Retention and deletion

Judgment rule: Record default retention for chats, files, indexes and logs; admin-configured retention; user deletion; deletion after contract end; and deletion confirmation.

LibreChat

Agent cross-checked Support: partial

Normal chats have no default expiry; temporary chats default to 30 days and admins can configure broader expiry modes.

Limitations

user_deletion: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified.
contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer.

default_retention What is retained and for how long by default? [supported]: The default temporary retention is 720 hours; normal chats persist unless configured under all/ephemeral modes. Memories do not expire with chats. Sources: librechat:librechat:retention.
admin_retention Can admins set retention periods? [supported]: Admins set all or ephemeral retention, regular/temporary deadlines and Agent file retention. New settings apply on later saves rather than rewriting every existing record immediately. Sources: librechat:librechat:retention.
user_deletion Can users delete their chats and files permanently? [partial]: Users can delete conversations/data and retention sweeps remove files. Copies, backups and external provider deletion were not end-to-end verified. Sources: librechat:librechat:retention, librechat:librechat:settings.
contract_end_deletion What is deleted at contract end, and when? [unknown]: contract_end_deletion: What is deleted at contract end, and when? No commercial contract-end purge/confirmation deadline was reviewed; the Demo’s retention terms are a separate offer.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:retention, librechat:librechat:settings.

Microsoft Copilot

Agent cross-checked Support: partial

Purview governs retained Exchange copies of managed Copilot interactions; uploaded-file repository retention is outside this finding.

Availability: generally-available · Delivery: native
Scope: surfaces=Microsoft Copilot Chat web app, Microsoft Copilot paid work chat; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Managed work/school Microsoft Copilot and Copilot Chat with EDP; Exchange prompt/response copies governed by applicable Purview retention/holds; add_ons=Eligible Microsoft365 tenant, Applicable Purview retention/eDiscovery licensing and configured policies; deployment_mode=multi-tenant-saas; region=Commercial cloud; EU/EFTA tenant scope where stated, including Switzerland; no government-cloud generalisation; os=not specified.

Limitations

Narrowed scope resolves the publication conflict for this finding: Exchange interaction copies are separate from uploaded-file repositories and temporary prompt context.
No universal18-month file-retention promise or immediate-deletion guarantee is made. Full repository/post-termination behavior needs a separate source/tenant check.

default_retention What is retained and for how long by default? [partial]: Prompts/responses are logged in Exchange; retention depends on tenant policies. A universal default duration for uploaded files/indexes is not established and is excluded from this Exchange-interaction scope. Sources: microsoft-copilot:ms-chat-privacy-r2, microsoft-copilot:ms-retention-r2.
admin_retention Can admins set retention periods? [supported]: Purview can retain/delete interaction copies; retention and eDiscovery holds can suspend permanent deletion. Sources: microsoft-copilot:ms-retention-r2.
user_deletion Can users delete their chats and files permanently? [partial]: Removing visible history does not immediately delete retained Exchange copies; retention/hold processing continues asynchronously. Sources: microsoft-copilot:ms-retention-r2.
contract_end_deletion What is deleted at contract end, and when? [unknown]: What is deleted at contract end, and when? Unverified after checking Purview retention and privacy documentation; complete post-termination deletion terms were not retrieved.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-chat-privacy-r2, microsoft-copilot:ms-retention-r2.

DATA-05 Sub-processors and foreign-law exposure

Judgment rule: Record the published sub-processor list with countries, change-notification rules, the vendor's and parent company's jurisdiction, transfer mechanisms (EU-US Data Privacy Framework, Swiss-US DPF, SCCs) and the vendor's documented position on foreign government access requests (e.g. US CLOUD Act). Record facts, not a legal assessment.

LibreChat

Agent cross-checked Support: partial

ClickHouse’s acquisition is sourced; the self-hosted deployment still selects its own external processors and contracts.

Limitations

subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
parent_jurisdiction: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement.
transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.

subprocessor_list Is a dated sub-processor list published? [unknown]: subprocessor_list: Is a dated sub-processor list published? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
subprocessor_countries Which countries do sub-processors operate in? [unknown]: subprocessor_countries: Which countries do sub-processors operate in? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
change_notification Are customers notified of sub-processor changes? [unknown]: change_notification: Are customers notified of sub-processor changes? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
parent_jurisdiction Which jurisdiction governs the vendor and its parent? [partial]: ClickHouse, Inc. announced the LibreChat acquisition on 2025-11-04 from San Francisco and brought founder/team into ClickHouse. A self-hosted customer contracting entity/governing jurisdiction was not established from that announcement. Sources: librechat:librechat:owner.
transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [unknown]: transfer_mechanism: Which transfer mechanism applies to non-EU/CH processing? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.
government_access_policy Is there a published government-access or transparency policy? [unknown]: government_access_policy: Is there a published government-access or transparency policy? No project-wide dated sub-processor/country list, change-notification schedule, transfer instrument or government-access policy was established for arbitrary customer-operated deployments. Website/Demo policies are separate scopes.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:owner.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft publishes subprocessor governance and change-notification routes; legal transfer details need direct contract review.

Limitations

Unverified parts: subprocessor_countries, parent_jurisdiction, transfer_mechanism, government_access_policy.
Read each atomic answer for its plan, access and feature limits.

subprocessor_list Is a dated sub-processor list published? [partial]: The AI subprocessor overview links the Online Services Subprocessors List; a dated country-by-country copy was not downloaded. Sources: microsoft-copilot:ms-subprocessors.
subprocessor_countries Which countries do sub-processors operate in? [unknown]: Which countries do sub-processors operate in? Unverified after checking AI subprocessor overview and linked Service Trust Portal; countries, contracting jurisdiction, transfer clauses and government-access policy not retrieved in this pass.
change_notification Are customers notified of sub-processor changes? [partial]: Customers can subscribe to list updates. Exact advance-notice periods were not established. Sources: microsoft-copilot:ms-subprocessors.
parent_jurisdiction Which jurisdiction governs the vendor and its parent? [unknown]: Which jurisdiction governs the vendor and its parent? Unverified after checking AI subprocessor overview and linked Service Trust Portal; countries, contracting jurisdiction, transfer clauses and government-access policy not retrieved in this pass.
transfer_mechanism Which transfer mechanism applies to non-EU/CH processing? [unknown]: Which transfer mechanism applies to non-EU/CH processing? Unverified after checking AI subprocessor overview and linked Service Trust Portal; countries, contracting jurisdiction, transfer clauses and government-access policy not retrieved in this pass.
government_access_policy Is there a published government-access or transparency policy? [unknown]: Is there a published government-access or transparency policy? Unverified after checking AI subprocessor overview and linked Service Trust Portal; countries, contracting jurisdiction, transfer clauses and government-access policy not retrieved in this pass.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-subprocessors.

DATA-06 Contracts and regulatory coverage

Judgment rule: Record DPA availability and form (click-through, negotiable), reference to Swiss revDSG and GDPR, governing law and court, EU AI Act documentation (provider or deployer role, transparency materials), and sector-specific materials (FINMA outsourcing, banking secrecy, public sector). No compliance verdict.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Microsoft Copilot

Agent cross-checked Support: partial

Enterprise data protection links a DPA and Product Terms; no regulatory compliance verdict is made.

Limitations

Unverified parts: governing_law, ai_act_materials, sector_materials.
Read each atomic answer for its plan, access and feature limits.

dpa Is a DPA available, and is it negotiable? [partial]: Microsoft says commercial Copilot/Chat are covered by its DPA and Product Terms; negotiability was not verified. Sources: microsoft-copilot:ms-edp.
revdsg_gdpr Does the DPA cover revDSG and GDPR? [partial]: The enterprise protection page names GDPR; Swiss revDSG wording was not inspected. Sources: microsoft-copilot:ms-edp.
governing_law Which law and court govern the contract? [unknown]: Which law and court govern the contract? Unverified after checking Enterprise data protection; the public DPA document index timed out, so law/court, AI Act and sector clauses remain unverified.
ai_act_materials Is EU AI Act documentation provided? [unknown]: Is EU AI Act documentation provided? Unverified after checking Enterprise data protection; the public DPA document index timed out, so law/court, AI Act and sector clauses remain unverified.
sector_materials Are FINMA or other sector materials provided? [unknown]: Are FINMA or other sector materials provided? Unverified after checking Enterprise data protection; the public DPA document index timed out, so law/court, AI Act and sector clauses remain unverified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-edp.

DATA-07 Certifications and attestations

Judgment rule: Record each certificate or report separately: ISO 27001, 27017, 27018, 27701, 42001; SOC 2 Type I/II with period; BSI C5; TISAX; national schemes. Record issuer, scope (which product and entity), validity and access route. A cloud provider's certificate does not certify the product.

LibreChat

No public information found Support: not-published

We found no public information on this. A missing finding is not evidence that the product lacks the capability.

Microsoft Copilot

Agent cross-checked Support: partial

BSI’s public registry verifies Microsoft 365 ISMS/privacy certificates with validity through July 28, 2027. A Copilot-specific certificate schedule and current SOC/C5 reports remain unverified.

Limitations

Registry verification covers the named Microsoft 365 ISMS/privacy scope; the issuer entries do not separately enumerate Copilot.
No restricted Service Trust Portal document, Copilot ISO 42001 certificate schedule, current SOC 2 audit period or C5 report was inspected.
Vendor-listed ISO 42001 scope is distinguished from issuer-verified ISO 27001/27701 metadata.

iso_27001 ISO 27001 with scope and validity? [partial]: BSI registry entry IS 552878 verifies Microsoft Corporation’s Microsoft 365 services ISMS against ISO/IEC 27001:2022, effective July 29, 2024 through July 28, 2027, under a February 14, 2024 applicability statement. Microsoft places Copilot under Microsoft 365 compliance commitments; the issuer entry does not separately enumerate Copilot, so exact app-scope verification remains incomplete. Sources: microsoft-copilot:microsoft-copilot:r5-bsi-iso27001, microsoft-copilot:microsoft-copilot:r5-copilot-compliance-boundary.
soc2 SOC 2 type, period and covered service? [unknown]: Unresolved on 2026-10-26. Searched https://servicetrust.microsoft.com/ViewPage/HomePageV2 and its public search index, https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2 and BSI’s Microsoft certificate directory. STP retrieval returned a JavaScript shell; indexed report/bridge-letter titles are not an inspected auditor opinion, audit period or Copilot-specific system description. No authenticated report was accessed.
c5 BSI C5 attestation? [unknown]: Unresolved on 2026-10-26. Searched https://servicetrust.microsoft.com/ViewPage/HomePageV2 and its public report index plus https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2 . Microsoft describes C5 controls in Office 365 SOC reporting, but a current C5 report and exact Copilot service scope/period were not retrieved; no Azure-only attestation was transferred to Copilot.
other_certifications Which other certificates (27701, 42001, TISAX)? [partial]: BSI PM 741035 verifies Microsoft 365 services’ processor privacy-management scope against ISO/IEC 27701:2019, effective July 29, 2024 through July 28, 2027. Microsoft’s public ISO 42001 page names Copilot/Chat, but its product-specific certificate issuer/validity were not obtained. No TISAX evidence or separately enumerated Copilot 27701 scope was verified. Sources: microsoft-copilot:microsoft-copilot:r5-bsi-iso27701, microsoft-copilot:microsoft-copilot:r5-iso42001-scope.
report_access How can customers obtain reports? [supported]: Customers use the Microsoft Service Trust Portal for audit reports. Some downloads require an Entra organizational cloud-services account and acceptance of a compliance-material NDA. No restricted document was accessed in this research. Sources: microsoft-copilot:microsoft-copilot:r4-report-access.
pentest Are independent penetration test summaries available? [partial]: STP documents a Pen Test and Security Assessments category for third-party attestations. No Copilot-specific assessment scope, date or summary was downloaded. Sources: microsoft-copilot:microsoft-copilot:r4-report-access.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:microsoft-copilot:r4-report-access, microsoft-copilot:microsoft-copilot:r5-bsi-iso27001, microsoft-copilot:microsoft-copilot:r5-bsi-iso27701, microsoft-copilot:microsoft-copilot:r5-copilot-compliance-boundary, microsoft-copilot:microsoft-copilot:r5-iso42001-scope.

DATA-08 Encryption and key control

Judgment rule: Record encryption at rest and in transit, customer-managed keys (BYOK/HYOK), key location, and private networking (private link, IP allow-lists, VPN).

LibreChat

Agent cross-checked Support: partial

Network and storage security depend on the customer’s deployment; application authentication does not certify encryption of all stored content.

Limitations

encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.
customer_managed_keys: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified.
tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.

encryption_at_rest Is data encrypted at rest? [unknown]: encryption_at_rest: Is data encrypted at rest? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.
customer_managed_keys Can the customer manage or hold the keys? [partial]: Operators own infrastructure and application secrets; a documented product HYOK/customer-managed content-encryption service was not verified. Sources: librechat:librechat:auth, librechat:librechat:compose-pin.
private_networking Is private connectivity or IP restriction available? [supported]: Operators deploy the stack on their own network and configure reverse proxies/HTTPS for remote access. Sources: librechat:librechat:remote, librechat:librechat:local.
tenant_isolation How are customers separated in shared SaaS? [unknown]: tenant_isolation: How are customers separated in shared SaaS? No default at-rest encryption guarantee covering MongoDB/files/PGVector or audited multi-tenant managed-service isolation was established from the installation guides.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:auth, librechat:librechat:compose-pin, librechat:librechat:remote, librechat:librechat:local.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft documents encryption and tenant separation; key-control coverage varies by component.

Limitations

Unverified parts: private_networking.
Read each atomic answer for its plan, access and feature limits.

encryption_at_rest Is data encrypted at rest? [supported]: Enterprise protection documents encryption at rest and in transit. Sources: microsoft-copilot:ms-edp.
customer_managed_keys Can the customer manage or hold the keys? [partial]: Agent Builder explicitly does not support customer-managed keys; this does not establish the key policy of every M365 workload. Sources: microsoft-copilot:ms-builder.
private_networking Is private connectivity or IP restriction available? [unknown]: Is private connectivity or IP restriction available? Unverified after checking enterprise data protection and Agent Builder limitations; private networking/IP restrictions and complete key-location matrix not established.
tenant_isolation How are customers separated in shared SaaS? [supported]: Microsoft documents separation of customer tenants; isolation was not tested. Sources: microsoft-copilot:ms-edp.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-edp, microsoft-copilot:ms-builder.

DATA-09 Professional secrecy

Judgment rule: For professional secrecy holders (Berufsgeheimnisträger: lawyers, doctors, auditors, tax advisers) under § 203 StGB (DE) and Art. 321 StGB (CH), record whether the vendor signs a contractual secrecy undertaking or a § 203 agreement that binds its staff and its sub-processors; whether this comes as a dedicated offering or a paid add-on, and on which plan; who can access content in plain text (vendor staff, sub-processors, model providers); and the documentation provided. A DPA or a no-training clause alone is not a secrecy undertaking. Banking secrecy and FINMA outsourcing belong to DATA-06, not here. Record contract facts, not a legal assessment.

LibreChat

Agent cross-checked Support: partial

Customer-operated message storage and configurable local/external inference establish part of the content-access boundary. A LibreChat-scoped staff/sub-processor secrecy undertaking or professional-secrecy offering remains unverified.

Availability: unknown · Delivery: unknown
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; message schema and reference Compose pinned to v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional commercial secrecy terms unverified. Public Demo and website policies checked only to distinguish their scope; add_ons=none stated; deployment_mode=on-premise; region=Customer-selected application, storage and model-service locations; no DE/CH professional-secrecy contract variant verified; os=not specified.

Limitations

The secrecy undertaking, sub-processor coverage, offering and professional-secrecy-specific documentation remain unknown.
content_access: Operator permissions, vendor/support grants, optional service access and provider staff access were not tested or contractually verified.
Technical data controls, a DPA, privacy wording and no-training statements do not establish the requested contractual undertaking. No legal compliance assessment is made.

secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: No LibreChat-scoped § 203 StGB / Art. 321 StGB undertaking binding vendor staff was obtained from the reviewed project documentation and public legal pages. The website privacy policy expressly excludes the self-hosted application; ClickHouse ownership does not establish a product-specific agreement. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner.
subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: No self-hosted LibreChat professional-secrecy annex or documented extension to sub-processors was obtained. The separate Demo policy describes processor instruction/security obligations, which do not establish the undertaking requested here or coverage of a customer deployment. Sources: librechat:librechat:secrecy-demo-policy.
secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: No dedicated professional-secrecy edition, paid add-on, eligible plan or price was established in the public project/legal materials and targeted searches. The public Demo is evaluation-only and excludes confidential or regulated data; it is a separate surface. Sources: librechat:librechat:demo.
content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: The pinned reference deployment mounts customer-controlled MongoDB, uploads and logs; the message schema declares ordinary text/content fields. This places host/database operators inside the application trust boundary (an architectural inference, not a permissions audit). The first-chat and endpoint guides route prompts to a selected local or external model with customer credentials. Vendor/support access, optional service operators and provider human access remain deployment- and contract-specific and unverified. Sources: librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom.
secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Public installation, endpoint and privacy documents describe technical data paths and distinguish website, Demo and self-hosted software. No LibreChat-specific DE/CH secrecy contract template, covered-party annex or professional-body guidance was located in the reviewed sources. Sources: librechat:librechat:firstchat, librechat:librechat:siteprivacy.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:siteprivacy, librechat:librechat:owner, librechat:librechat:secrecy-demo-policy, librechat:librechat:demo, librechat:librechat:compose-pin, librechat:librechat:secrecy-message-pin, librechat:librechat:firstchat, librechat:librechat:custom.

Microsoft Copilot

Agent cross-checked Support: partial

Commercial data protection and model-specific access safeguards are documented; a scoped professional-secrecy undertaking was not verified.

Availability: unknown · Delivery: unknown
Scope: surfaces=Microsoft Copilot Chat web app, Microsoft Copilot paid work chat, Copilot in Microsoft 365 apps and Teams, Microsoft Copilot desktop and mobile clients; version=Continuously updated commercial service, retrieved 2026-10-21; plan=Microsoft Copilot Chat with eligible Microsoft 365 subscription; paid Microsoft Copilot add-on where stated; add_ons=Qualifying Microsoft 365 base licence, Purview and SharePoint Advanced Management entitlements where stated, Copilot Credits usage-based billing for Cowork and other metered features where stated; deployment_mode=multi-tenant-saas; region=German §203 StGB and Swiss Art.321 StGB use cases; existing hosting, support and provider-location exceptions still apply.; os=not specified.

Limitations

General confidentiality, a DPA and no-training commitments do not establish a professional-secrecy undertaking. No vendor/sales contact or agreement signing was performed.
No legal compliance verdict; unknown does not mean the offering is unavailable.

secrecy_undertaking Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? [unknown]: Does the vendor sign a secrecy undertaking or § 203 StGB / Art. 321 StGB agreement covering its own staff? Unverified after checking commercial Copilot/Chat enterprise-data-protection, privacy, EU Data Boundary and Anthropic processing pages, plus official-domain searches for professional secrecy, §203 and Art.321. The Microsoft-hosted German data-secrecy amendment PDF redirected to login, so its current text, Copilot plan coverage, subprocessor obligations, signatures, price and Swiss applicability were not verified.
subprocessor_coverage Does the undertaking extend to its sub-processors, and is that documented? [unknown]: Does the undertaking extend to its sub-processors, and is that documented? Unverified after checking commercial Copilot/Chat enterprise-data-protection, privacy, EU Data Boundary and Anthropic processing pages, plus official-domain searches for professional secrecy, §203 and Art.321. The Microsoft-hosted German data-secrecy amendment PDF redirected to login, so its current text, Copilot plan coverage, subprocessor obligations, signatures, price and Swiss applicability were not verified.
secrecy_offering Is it a dedicated offering or add-on, and on which plan? [unknown]: Is it a dedicated offering or add-on, and on which plan? Unverified after checking commercial Copilot/Chat enterprise-data-protection, privacy, EU Data Boundary and Anthropic processing pages, plus official-domain searches for professional secrecy, §203 and Art.321. The Microsoft-hosted German data-secrecy amendment PDF redirected to login, so its current text, Copilot plan coverage, subprocessor obligations, signatures, price and Swiss applicability were not verified.
content_access Who can access content in plain text: vendor staff, sub-processors, model providers? [partial]: Microsoft documents Azure OpenAI abuse-monitoring human-review exclusion and distinguishes optional Anthropic subprocessor models from models under separate retention terms. This does not establish a complete staff/subprocessor plain-text access matrix or a §203/Art.321 restriction. Sources: microsoft-copilot:ms-no-training, microsoft-copilot:ms-anthropic, microsoft-copilot:ms-eudb.
secrecy_documentation Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? [unknown]: Is the offering publicly documented (contract template, data-flow description, professional-body guidance)? Unverified after checking commercial Copilot/Chat enterprise-data-protection, privacy, EU Data Boundary and Anthropic processing pages, plus official-domain searches for professional secrecy, §203 and Art.321. The Microsoft-hosted German data-secrecy amendment PDF redirected to login, so its current text, Copilot plan coverage, subprocessor obligations, signatures, price and Swiss applicability were not verified.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-no-training, microsoft-copilot:ms-anthropic, microsoft-copilot:ms-eudb.

Commercials and vendor

VEN-01 Pricing model and list prices

Judgment rule: Record pricing unit (per seat, per active user, usage-based, platform fee, hybrid), list prices per plan in original currency with date, included usage and credits, add-on prices (connectors, agents, image generation) and overage rates. Cite public prices or dated quotes. Per-seat versus usage is a fact, not a quality judgment.

LibreChat

Agent cross-checked Support: partial

MIT software has no licence subscription; hosting, inference and optional runtime services are separately procured.

Limitations

add_ons: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts.
overage: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff.

pricing_unit What is the pricing unit? [supported]: The pinned MIT permission grant has no per-user fee; self-hosting and model accounts are customer responsibilities. Sources: librechat:librechat:license, librechat:librechat:firstchat.
list_prices What are list prices per plan, with date and currency? [supported]: The repository’s MIT licence permits use without a software fee as retrieved 2026-10-21; there is no bundled inference subscription in this scope. Sources: librechat:librechat:license, librechat:librechat:firstchat.
included_usage What usage is included? [supported]: LibreChat ships with no model API key and no included provider token balance. Sources: librechat:librechat:firstchat.
add_ons Which features cost extra? [partial]: Optional external code/OCR/search/image services need separately configured endpoints and credentials. Their rates depend on the operator’s contracts. Sources: librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images.
overage What do usage beyond limits and premium models cost? [partial]: Provider APIs charge their account holder; internal credit balances are governance configuration rather than a single LibreChat usage tariff. Sources: librechat:librechat:balance, librechat:librechat:tokens, librechat:librechat:firstchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:firstchat, librechat:librechat:code, librechat:librechat:ocr, librechat:librechat:web, librechat:librechat:images, librechat:librechat:balance, librechat:librechat:tokens.

Microsoft Copilot

Agent cross-checked Support: partial

Pricing combines seat licensing with usage-based extensions and base-suite prerequisites.

Limitations

Read each atomic answer for its plan, access and feature limits.

pricing_unit What is the pricing unit? [supported]: Paid Copilot is a per-user add-on; Chat is included with eligible M365 and some extensions are metered. Sources: microsoft-copilot:ms-price-us.
list_prices What are list prices per plan, with date and currency? [supported]: Retrieved 2026-10-21: US USD 30/user/month billed annually; Germany EUR 26/user/month billed annually, excluding VAT. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-price-de.
included_usage What usage is included? [partial]: Paid users have included qualifying assistive-agent usage; exact limits and exclusions depend on the scenario. Sources: microsoft-copilot:ms-credit-rates.
add_ons Which features cost extra? [supported]: Qualifying M365 licensing is separate; Cowork is metered and compliance tools can need further entitlements. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-setup.
overage What do usage beyond limits and premium models cost? [partial]: Credits have feature-dependent rates; prepaid exhaustion may continue into PAYG. Currency-per-credit and full premium-model rate mapping were not retrieved. Sources: microsoft-copilot:ms-credit-rates, microsoft-copilot:ms-cost-setup.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-us, microsoft-copilot:ms-price-de, microsoft-copilot:ms-credit-rates, microsoft-copilot:ms-setup, microsoft-copilot:ms-cost-setup.

VEN-02 Scenario cost

Judgment rule: Price three workloads for 12 months: 200, 1,000 and 5,000 users with a disclosed light/regular/power usage mix, in CHF and EUR excluding VAT. Include licences, platform fees, add-ons, model usage and, for self-hosted options, a stated operating assumption. Separate fixed, variable, included and unknown costs. No invented discounts.

LibreChat

Agent cross-checked Support: partial

ALM-14 shared cost assumptions v1.4, 2026-10-21: zero standard licence plus a disclosed Swiss infrastructure/operations and direct-BYO-model budget. Annual CHF/EUR figures are floors plus named unknown costs.

Availability: generally-available · Delivery: native
Scope: surfaces=Customer-operated web application and server; version=Public documentation retrieved 2026-10-21; inspected source v0.8.8 / e8f3be08623663d4ad7f7241e693c94469b63bb0; plan=MIT customer-operated LibreChat; optional separately deployed services identified per answer; add_ons=Analyst-selected direct OpenAI API proxy, not a bundled model, Assumed operations staffing; optional commercial services excluded; deployment_mode=customer-cloud; region=Azure Switzerland North for the reference application infrastructure; standard OpenAI API inference has no Swiss/EU residency assumption; os=not specified.

Limitations

ALM-14 shared cost assumptions v1.4, 2026-10-21 are analyst inputs, not vendor sizing or an uptime promise.
The budget is a floor because named infrastructure and service costs are unpriced.

cost_200 Year-one cost at 200 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 200 users, 12 months excluding VAT: from CHF 34778.28 / EUR 37651.06 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 4749.26, operations CHF 30000.00, and BYO model usage USD 475.20. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
cost_1000 Year-one cost at 1,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 1,000 users, 12 months excluding VAT: from CHF 88600.40 / EUR 95919.02 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 12605.23, operations CHF 75000.00, and BYO model usage USD 2376.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
cost_5000 Year-one cost at 5,000 users? [partial]: ALM-14 shared cost assumptions v1.4, 2026-10-21. 5,000 users, 12 months excluding VAT: from CHF 189541.24 / EUR 205197.83 plus unpriced items. Includes zero standard-software licence, reference infrastructure EUR 32214.49, operations CHF 150000.00, and BYO model usage USD 11880.00. This is an assumption-based budget floor, not a vendor quote or validated capacity plan. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.
variable_share Which part depends on usage? [partial]: Shared mix is 60% light at 100, 30% regular at 400 and 10% power at 1,500 messages/user/month, or 330 weighted messages. Each message is 3,000 input and 600 output tokens. Direct BYO proxy is gpt-6-luna, reasoning effort none, Standard short-context uncached rates USD 0.10/0.50 per million input/output tokens. It costs USD 2.376/user/year before optional tools, embedding, caching or regional processing. This proxy is an analyst assumption, not the product default. Sources: librechat:librechat:cost-model, librechat:librechat:cost-effort.
unknown_parts Which costs could not be priced? [partial]: Unpriced additions are file/object storage beyond the assumed 500 GB PostgreSQL storage, VM OS/data disks, backup excess, egress/load balancers, Redis or additional database services, high availability, embeddings, OCR, search, audio/images, integration work and optional commercial services. MongoDB remains the primary store, so its infrastructure, file storage and other required dependencies are additional unpriced items; PostgreSQL is only the shared RAG/reference compute assumption. The shared VM/PG sizes have not been load-tested and do not replace each product’s documented runtime dependencies. Sources: librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:cost-vm, librechat:librechat:cost-pg, librechat:librechat:cost-fx, librechat:librechat:cost-model, librechat:librechat:cost-effort.

Microsoft Copilot

Agent cross-checked Support: partial

A reproducible licence-only scenario is available; full rollout cost remains open.

Limitations

Shared assumptions v1.3; ECB 2026-10-20 EUR 1 = USD 1.1215 = CHF 0.9237. The stated mix is a research assumption, not an observed workload or entitlement.
Full totals remain baseline + unknown because additional licences, workload capacity, optional support and deployment costs were not priced.

cost_200 Year-one cost at 200 users? [partial]: From EUR 62400.00 + unknown, or CHF 57638.88 + unknown, for 12 months excluding VAT. Licence-only incremental add-on baseline at EUR 26/user/month; eligible M365 licences assumed already owned. ALM-14 shared cost assumptions v1.4, 2026-10-21: 60% light at 100, 30% regular at 400, 10% power at 1,500 messages/user/month; 3,000 input and 600 output tokens/message where usage is billed separately. No metered agent/Cowork usage or discounts assumed; included-capacity sufficiency is unverified. Sources: microsoft-copilot:ms-price-de, microsoft-copilot:fx-20261020.
cost_1000 Year-one cost at 1,000 users? [partial]: From EUR 312000.00 + unknown, or CHF 288194.40 + unknown, for 12 months excluding VAT. Licence-only incremental add-on baseline at EUR 26/user/month; eligible M365 licences assumed already owned. ALM-14 shared cost assumptions v1.4, 2026-10-21: 60% light at 100, 30% regular at 400, 10% power at 1,500 messages/user/month; 3,000 input and 600 output tokens/message where usage is billed separately. No metered agent/Cowork usage or discounts assumed; included-capacity sufficiency is unverified. Sources: microsoft-copilot:ms-price-de, microsoft-copilot:fx-20261020.
cost_5000 Year-one cost at 5,000 users? [partial]: From EUR 1560000.00 + unknown, or CHF 1440972.00 + unknown, for 12 months excluding VAT. Licence-only incremental add-on baseline at EUR 26/user/month; eligible M365 licences assumed already owned. ALM-14 shared cost assumptions v1.4, 2026-10-21: 60% light at 100, 30% regular at 400, 10% power at 1,500 messages/user/month; 3,000 input and 600 output tokens/message where usage is billed separately. No metered agent/Cowork usage or discounts assumed; included-capacity sufficiency is unverified. Sources: microsoft-copilot:ms-price-de, microsoft-copilot:fx-20261020.
variable_share Which part depends on usage? [partial]: Cowork and uncovered agent/credit usage add variable charges. No model/task tariff is substituted where the product does not publish the required rate. Sources: microsoft-copilot:ms-price-us.
unknown_parts Which costs could not be priced? [partial]: Base-suite renewal costs, metered workload, usage headroom, implementation and optional compliance/support charges remain unpriced. Sources: microsoft-copilot:ms-price-us.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-de, microsoft-copilot:fx-20261020, microsoft-copilot:ms-price-us.

VEN-03 Evaluation access

Judgment rule: Distinguish free tier, self-serve trial, sales-led pilot, paid proof of concept and open-source self-install. Record card requirement, duration, seat limit, and which features (SSO, connectors, admin) the trial includes. Map which shared scenarios can be run without sales approval.

LibreChat

Agent cross-checked Support: supported

Customers can self-install without licence payment; the public demo is an evaluation-only alternative.

free_tier Is there a free tier for business use? [supported]: MIT self-installation permits organizational use without a software licence fee. Sources: librechat:librechat:license.
self_serve_trial Is a self-serve business trial available? [supported]: Self-installation has no trial clock or software card requirement; the free hosted Demo can be tried separately under its terms. Sources: librechat:librechat:local, librechat:librechat:demo.
trial_scope Do trials include SSO, connectors and admin features? [supported]: Self-installed instances can configure SSO, Agents, file retrieval and administration with their own service accounts. It is not evidence that every experimental add-on is enabled by default. Sources: librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag.
sales_gate Does meaningful evaluation require sales contact? [supported]: The documented Docker install does not require sales approval; optional third-party services have separate account requirements. Sources: librechat:librechat:local, librechat:librechat:firstchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:demo, librechat:librechat:auth, librechat:librechat:agents, librechat:librechat:rag, librechat:librechat:firstchat.

Microsoft Copilot

Agent cross-checked Support: partial

Eligible M365 users can evaluate Copilot Chat directly; paid pilot terms remain unverified.

Limitations

Unverified parts: sales_gate.
Read each atomic answer for its plan, access and feature limits.

free_tier Is there a free tier for business use? [supported]: Chat has no incremental charge for eligible M365 work accounts, with enterprise protections. Sources: microsoft-copilot:ms-price-us.
self_serve_trial Is a self-serve business trial available? [partial]: The enterprise page offers Chat access as the evaluation path; a timed paid add-on trial was not established. Sources: microsoft-copilot:ms-price-us.
trial_scope Do trials include SSO, connectors and admin features? [partial]: Chat includes enterprise protection and agent management, but full paid work grounding and other enterprise scenarios need their prerequisites. Sources: microsoft-copilot:ms-price-us.
sales_gate Does meaningful evaluation require sales contact? [unknown]: Does meaningful evaluation require sales contact? Unverified after checking enterprise pricing FAQ; no signup, card check or enterprise trial was performed.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-us.

VEN-04 Contract terms and pricing transparency

Judgment rule: Record minimum seats or commitment, contract length, monthly versus annual billing, price-change rules, cancellation and downgrade terms, and invoicing in CHF/EUR. Classify pricing as transparent, partially specified, quote-only or unknown, naming the missing fields. Quote-only pricing is a disclosed constraint.

LibreChat

Agent cross-checked Support: partial

The MIT licence has no seat or contract-term subscription; optional service contracts are outside that licence.

Limitations

cancellation: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies.
local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services.
transparency_class: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer.

minimum_commitment What seat or spend minimum applies? [supported]: The MIT permission grant has no user-count or spending minimum for software use. Sources: librechat:librechat:license.
contract_length What contract lengths are offered? [supported]: There is no monthly/annual licence subscription in the MIT permission grant. External hosting/API contracts are separate. Sources: librechat:librechat:license.
cancellation How can the contract be cancelled or reduced? [partial]: An operator can stop running the application; this does not cancel its separately purchased cloud/model services or establish deletion of all copies. Sources: librechat:librechat:license, librechat:librechat:local.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [unknown]: local_invoicing: Can it be invoiced in CHF or EUR from a European entity? CHF/EUR commercial invoicing from a European entity was not established for optional project services.
transparency_class Is pricing transparent, partial, quote-only or unknown? [partial]: Source licensing is transparent; a complete all-in hosted/support/inference tariff is not included in this self-hosted offer. Sources: librechat:librechat:license, librechat:librechat:firstchat.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:local, librechat:librechat:firstchat.

Microsoft Copilot

Agent cross-checked Support: partial

Public seat prices are visible; procurement and cancellation details remain partly specified.

Limitations

Unverified parts: minimum_commitment, cancellation, local_invoicing.
Read each atomic answer for its plan, access and feature limits.

minimum_commitment What seat or spend minimum applies? [unknown]: What seat or spend minimum applies? Unverified after checking enterprise price cards and FAQ; seat minimums, downgrade/cancellation rules and contracting-entity currency terms not retrieved.
contract_length What contract lengths are offered? [supported]: The quoted add-on price uses annual auto-renewing subscription billing. Sources: microsoft-copilot:ms-price-de.
cancellation How can the contract be cancelled or reduced? [unknown]: How can the contract be cancelled or reduced? Unverified after checking enterprise price cards and FAQ; seat minimums, downgrade/cancellation rules and contracting-entity currency terms not retrieved.
local_invoicing Can it be invoiced in CHF or EUR from a European entity? [unknown]: Can it be invoiced in CHF or EUR from a European entity? Unverified after checking enterprise price cards and FAQ; seat minimums, downgrade/cancellation rules and contracting-entity currency terms not retrieved.
transparency_class Is pricing transparent, partial, quote-only or unknown? [partial]: Partially specified: list seat prices exist, while base licensing, metered services and negotiated terms change total cost. Sources: microsoft-copilot:ms-price-de, microsoft-copilot:ms-price-us.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-price-de, microsoft-copilot:ms-price-us.

VEN-05 Source licence

Judgment rule: Record licence per component (client, server, connectors, hosted extensions) and revision. Distinguish OSI open source, source-available with restrictions (branding clauses, user caps), and closed. Repository visibility is not a licence classification. Licences change between releases: record the current terms, and never carry a fork's historical licence over to the upstream product or the reverse.

LibreChat

Agent cross-checked Support: partial

The pinned main repository is MIT licensed; no user-count or product-branding clause appears in that licence.

Limitations

enterprise_features_closed: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established.

licence_type Which licence applies to each component? [supported]: The main client/server repository at v0.8.8 is MIT. Separate Code Interpreter, admin-panel, connector or hosted-service components need their own licence review. Sources: librechat:librechat:license.
branding_restrictions Do licence terms restrict branding or user counts? [supported]: The MIT grant permits use/modification/distribution subject to retaining its copyright and permission notice; it includes no 50-user cap or mandatory UI branding clause. Sources: librechat:librechat:license.
enterprise_features_closed Are enterprise features in a separate closed edition? [partial]: The project documents a separate preview admin panel and optional code services. A closed enterprise-edition boundary for the main repository was not established. Sources: librechat:librechat:admin, librechat:librechat:code, librechat:librechat:license.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:license, librechat:librechat:admin, librechat:librechat:code.

Microsoft Copilot

Agent cross-checked Support: partial

Commercial hosted-service use is governed by restrictive Microsoft licence terms; component source licences remain unverified.

Limitations

This records hosted-service contractual rights, not an audited licence inventory for every client, sample or connector.

licence_type Which licence applies to each component? [partial]: The hosted commercial service uses Microsoft Online Services Product Terms. Use is limited to the licensing agreement, rights are reserved, and reverse engineering is restricted. Individual client and connector source licences were not inventoried. Sources: microsoft-copilot:microsoft-copilot:r4-online-service-terms.
branding_restrictions Do licence terms restrict branding or user counts? [unknown]: Do licence terms restrict branding or user counts? Unverified after checking Microsoft product, licensing and Agent Builder documentation; no service/client/connector source-licence inventory or current product licence grant was inspected.
enterprise_features_closed Are enterprise features in a separate closed edition? [unknown]: Are enterprise features in a separate closed edition? Unverified after checking Microsoft product, licensing and Agent Builder documentation; no service/client/connector source-licence inventory or current product licence grant was inspected.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:microsoft-copilot:r4-online-service-terms.

VEN-06 Data export and exit

Judgment rule: Record admin export of chats, assistants, knowledge bases, prompts and audit logs, formats, export completeness, user self-export, and what survives contract end. Run an admin export on a trial. Exported chats alone do not make assistants and knowledge portable.

LibreChat

Agent cross-checked Support: partial

Users can export conversations in machine-readable formats; organization-wide Agent/knowledge exit completeness remains unverified.

Limitations

chat_export: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established.
assistant_export: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified.
knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.
post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.

chat_export Can admins export all chats? [partial]: Pinned client code exports a user-selected conversation, including optional branches/options. A documented admin bulk export of every user’s chats was not established. Sources: librechat:librechat:export-pin.
assistant_export Can assistants and prompts be exported in a reusable format? [partial]: Beta management APIs expose Agent/Skill objects, but a reusable complete assistant/prompt export fixture was not verified. Sources: librechat:librechat:api.
knowledge_export Can knowledge bases and their sources be exported? [unknown]: knowledge_export: Can knowledge bases and their sources be exported? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.
export_format Are formats documented and machine-readable? [supported]: Conversation export code supports JSON, CSV, Markdown and text. This establishes format availability, not complete organization-data portability. Sources: librechat:librechat:export-pin.
post_termination_window How long can data be retrieved after termination? [unknown]: post_termination_window: How long can data be retrieved after termination? No admin exit fixture, knowledge-source/index portability test or commercial post-termination retrieval window was verified; infrastructure backups are operator-owned.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:export-pin, librechat:librechat:api.

Microsoft Copilot

Agent cross-checked Support: partial

Compliance search/export is distinct from a reusable complete workspace exit.

Limitations

Unverified parts: assistant_export, knowledge_export, post_termination_window.
Read each atomic answer for its plan, access and feature limits.

chat_export Can admins export all chats? [partial]: Microsoft documents Content search/Purview access and Teams Export APIs for stored interaction data; completeness across every chat surface was not tested. Sources: microsoft-copilot:ms-privacy.
assistant_export Can assistants and prompts be exported in a reusable format? [unknown]: Can assistants and prompts be exported in a reusable format? Unverified after checking Copilot privacy, retention and Agent Builder documentation; no admin export or post-contract retrieval test.
knowledge_export Can knowledge bases and their sources be exported? [unknown]: Can knowledge bases and their sources be exported? Unverified after checking Copilot privacy, retention and Agent Builder documentation; no admin export or post-contract retrieval test.
export_format Are formats documented and machine-readable? [partial]: Teams has an export API route; a complete reusable chat/assistant/knowledge format was not established. Sources: microsoft-copilot:ms-privacy.
post_termination_window How long can data be retrieved after termination? [unknown]: How long can data be retrieved after termination? Unverified after checking Copilot privacy, retention and Agent Builder documentation; no admin export or post-contract retrieval test.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-privacy.

VEN-07 Support and service levels

Judgment rule: Record support channels, languages (German, French, Italian), hours and time zone, local or regional presence, documented response times, uptime SLA and credits, public status page and incident history. Popularity is not a reliability score.

LibreChat

Agent cross-checked Support: partial

Public project/community channels are available; a binding business support SLA was not established.

Limitations

support_channels: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting.
support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.

support_channels Which support channels are available on each plan? [partial]: Public GitHub issue reporting and community channels are documented; a supported enterprise channel/response-time matrix was not established for MIT self-hosting. Sources: librechat:librechat:logging, librechat:librechat:firstchat.
support_languages Is support available in German, French or Italian? [unknown]: support_languages: Is support available in German, French or Italian? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: regional_presence: Is there a DACH or Swiss entity, team or partner? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
uptime_sla Is there an uptime SLA with credits? [unknown]: uptime_sla: Is there an uptime SLA with credits? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.
status_page Is there a public status page with history? [unknown]: status_page: Is there a public status page with history? No DE/FR/IT support coverage, CH/DACH legal/partner presence, priced uptime credits or product-service incident-history contract was verified in the public docs, site and release pass.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:logging, librechat:librechat:firstchat.

Microsoft Copilot

Agent cross-checked Support: partial

Copilot support entry points are documented; plan-specific response, language and SLA commitments remain gaps.

Limitations

Developer/extensibility support route only; no support case or sales request was opened.

support_channels Which support channels are available on each plan? [partial]: Copilot service/development support uses Admin Center Help and Support; the extensibility guide ties service requests to a Premier/Unified support agreement. General questions can use Microsoft Q&A. A complete plan/language/SLA matrix was not retrieved. Sources: microsoft-copilot:microsoft-copilot:r4-support-channels.
support_languages Is support available in German, French or Italian? [unknown]: Is support available in German, French or Italian? Unverified after checking https://status.cloud.microsoft/ returned a JavaScript-only shell; Copilot setup and enterprise plans did not establish language-specific support hours, regional team, response targets or applicable SLA credits.
regional_presence Is there a DACH or Swiss entity, team or partner? [unknown]: Is there a DACH or Swiss entity, team or partner? Unverified after checking https://status.cloud.microsoft/ returned a JavaScript-only shell; Copilot setup and enterprise plans did not establish language-specific support hours, regional team, response targets or applicable SLA credits.
uptime_sla Is there an uptime SLA with credits? [unknown]: Is there an uptime SLA with credits? Unverified after checking https://status.cloud.microsoft/ returned a JavaScript-only shell; Copilot setup and enterprise plans did not establish language-specific support hours, regional team, response targets or applicable SLA credits.
status_page Is there a public status page with history? [unknown]: Is there a public status page with history? Unverified after checking https://status.cloud.microsoft/ returned a JavaScript-only shell; Copilot setup and enterprise plans did not establish language-specific support hours, regional team, response targets or applicable SLA credits.

Checked 2026-10-26; agent cross-checked 2026-10-26; check again by 2026-12-25. Sources: microsoft-copilot:microsoft-copilot:r4-support-channels.

VEN-08 Onboarding, training and adoption

Judgment rule: Record vendor-led onboarding, admin training, end-user training (live, e-learning, languages), use-case libraries, champion programmes, change-management materials and their cost. Distinguish included services from paid professional services and partner offerings.

LibreChat

Agent cross-checked Support: partial

Self-hosting and Agent use have public setup guides; vendor-led training/adoption packages were not verified.

Limitations

onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
use_case_library: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established.
adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.

onboarding_service Is guided onboarding included? [unknown]: onboarding_service: Is guided onboarding included? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
user_training Is end-user training offered, in which languages? [unknown]: user_training: Is end-user training offered, in which languages? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
use_case_library Are role-based use cases and templates provided? [partial]: The Agent and setup guides include examples and tutorials; a role-based enterprise training/use-case program was not established. Sources: librechat:librechat:agents, librechat:librechat:firstchat.
adoption_programme Is there a champion or adoption programme? [unknown]: adoption_programme: Is there a champion or adoption programme? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.
service_cost Which services cost extra? [unknown]: service_cost: Which services cost extra? No included guided rollout, local-language end-user training, champion programme, change-management service or professional-service price list was established from the official documentation and site.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: librechat:librechat:agents, librechat:librechat:firstchat.

Microsoft Copilot

Agent cross-checked Support: partial

Microsoft publishes role-based learning and adoption materials.

Limitations

Unverified parts: onboarding_service, service_cost.
Read each atomic answer for its plan, access and feature limits.

onboarding_service Is guided onboarding included? [unknown]: Is guided onboarding included? Unverified after checking Copilot Skilling Center and commercial resources; included onboarding entitlements, service language and professional-service fees not established.
user_training Is end-user training offered, in which languages? [partial]: The Skilling Center lists Academy learning, webinars and instructor-led events; exact DE/FR/IT delivery was not checked. Sources: microsoft-copilot:ms-training.
use_case_library Are role-based use cases and templates provided? [supported]: Copilot Prompt Gallery offers starter prompts. Sources: microsoft-copilot:ms-price-us.
adoption_programme Is there a champion or adoption programme? [supported]: Microsoft links its Champion programme and adoption resources. Sources: microsoft-copilot:ms-training.
service_cost Which services cost extra? [unknown]: Which services cost extra? Unverified after checking Copilot Skilling Center and commercial resources; included onboarding entitlements, service language and professional-service fees not established.

Checked 2026-10-21; agent cross-checked 2026-10-21; check again by 2026-12-20. Sources: microsoft-copilot:ms-training, microsoft-copilot:ms-price-us.

Sources

Custom endpoints librechat:librechat:custom
Operators configure compatible endpoints and customer-held keys, including local and hosted services.
Endpoint setup; API key; base URL; model list · documented · Source date not stated · Retrieved 2026-10-21
Azure OpenAI configuration librechat:librechat:azure
Azure OpenAI uses customer deployment groups, instance names and credentials.
Deployment groups; API credentials · documented · Source date not stated · Retrieved 2026-10-21
AWS Bedrock object structure librechat:librechat:bedrock
Bedrock routes use customer AWS configuration and region selection.
Region; credentials; model selection · documented · Source date not stated · Retrieved 2026-10-21
Anthropic Vertex AI configuration librechat:librechat:vertex
Claude can run through customer Google Vertex AI credentials and regions.
Project and region configuration · documented · Source date not stated · Retrieved 2026-10-21
Model specifications librechat:librechat:modelspec
Administrators can enforce configured model presets and defaults; available endpoints still depend on customer credentials.
enforce; preset; modelSelect; addedEndpoints · documented · Source date not stated · Retrieved 2026-10-21
Agents librechat:librechat:agents
Agents combine instructions, models, files, tools, skills and sharing permissions, with visible execution and configurable approval.
Builder; Capabilities; Version history; Sharing; Activity; tool approval · documented · Source date not stated · Retrieved 2026-10-21
OCR for documents librechat:librechat:ocr
OCR can augment text extraction, or files can be sent to compatible provider APIs; format and model limitations remain.
File Context; Upload as Text; Optional OCR; Limitations · documented · Source date not stated · Retrieved 2026-10-21
LibreChat v0.8.8 release librechat:librechat:releases
The stable release documents agent controls, current model updates and explicitly experimental schedules/workspaces and beta Agents API.
Highlights, 2026-10-01 · documented · Source date 2026-10-01 · Retrieved 2026-10-21
Choose your model when editing with Copilot in PowerPoint microsoft-copilot:ms-ppt-model-r2
Commercial PowerPoint editing documents Auto, ChatGPT and Claude choices, with Anthropic admin enablement and session/region limits.
Commercial subscription requirement; editing-mode selector; session and region limits · documented · Source date not stated · Retrieved 2026-10-21
AI at Work Roadmap microsoft-copilot:ms-roadmap
The roadmap contains dated model launches, identifies Office in Copilot as Frontier and lists Cowork as generally available.
September model entries; October 9 Office Frontier; June 16 Cowork GA · vendor-claimed · Source date not stated · Retrieved 2026-10-21
Microsoft 365 Copilot release notes microsoft-copilot:ms-release
Release notes distinguish platform availability and describe gradual tenant rollout.
October 6 2026; gradual release policy · documented · Source date 2026-10-06 · Retrieved 2026-10-21
Your first chat librechat:librechat:firstchat
LibreChat ships without a model key; the public demo is for evaluation rather than private or durable data.
Software you host yourself; endpoint credentials; public demo · documented · Source date not stated · Retrieved 2026-10-21
Code Interpreter API librechat:librechat:code
A separate code execution service supports multiple languages and downloadable generated files; stateful/attached modes are experimental.
Setup; self-hosted service; workspace permissions; generated files · documented · Source date not stated · Retrieved 2026-10-21
LibreChat v0.8.8 MIT licence librechat:librechat:license
The pinned repository is MIT licensed with copyright/permission notice preservation and an as-is disclaimer.
LICENSE, permission grant and notice requirement · documented · Source date not stated · Retrieved 2026-10-21
RAG API configuration librechat:librechat:ragcfg
OpenAI, Hugging Face and Ollama embedding configurations are documented; image choice affects local embedding support.
Embedding providers; lite image; full image · documented · Source date not stated · Retrieved 2026-10-21
Granular access control librechat:librechat:access
Roles, groups and resource ACLs govern features and sharing, with Entra groups synchronized at sign-in.
Feature permissions; Resource ACLs; System grants; Groups · documented · Source date not stated · Retrieved 2026-10-21
LibreChat Admin Panel librechat:librechat:admin
A separate browser management panel is available for testing and uses the underlying LibreChat admin APIs.
Status Preview; separate service; admin APIs · documented · Source date not stated · Retrieved 2026-10-21
Balance configuration librechat:librechat:balance
Optional token-credit balances initialize and refill user credits; tracking is disabled by default.
enabled; startBalance; refill configuration · documented · Source date not stated · Retrieved 2026-10-21
Automated moderation librechat:librechat:mod
Moderation scores abusive login/registration/message activity and may ban users; it is not a documented content DLP classifier.
Violation scoring and limits · documented · Source date not stated · Retrieved 2026-10-21
LibreChat balance admission implementation librechat:librechat:balance-pin
The pinned middleware reserves user credits and throws a TOKEN_BALANCE error when the reservation cannot be admitted.
packages/api/src/middleware/checkBalance.ts, checkBalance · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path packages/api/src/middleware/checkBalance.ts
Anthropic models in Microsoft Online Services microsoft-copilot:ms-anthropic
Anthropic is disabled by default for EU/EFTA/UK tenants, excluded from EU/in-country processing commitments, and retention-labelled models have separate terms.
Opt-in regions; admin settings; Anthropic models with Data Retention · documented · Source date not stated · Retrieved 2026-10-21
Microsoft Copilot Plans and Pricing - Enterprise microsoft-copilot:ms-price-us
The US page lists Copilot Chat at no additional cost with eligible M365, a USD 30 annual-billing monthly add-on, separate base licensing and metered agent/Cowork use.
Copilot Chat; paid add-on; compare plans; FAQ · vendor-claimed · Source date not stated · Retrieved 2026-10-21
RAG API librechat:librechat:rag
A separate RAG API indexes uploaded content in PostgreSQL/PGVector for retrieval.
Architecture; document indexing; embeddings; semantic search · documented · Source date not stated · Retrieved 2026-10-21
Upload files as text librechat:librechat:text
Text upload injects extracted file content rather than relying only on vector retrieval.
Full text extraction and context · documented · Source date not stated · Retrieved 2026-10-21
File configuration librechat:librechat:filecfg
File limits and formats are configurable by endpoint and file processing route.
File limits; MIME patterns; provider routes · documented · Source date not stated · Retrieved 2026-10-21
LibreChat spreadsheet text parser librechat:librechat:r4-spreadsheet-parser
The built-in parser accepts XLSX/XLS/ODS and serializes each sheet as its name followed by CSV values. It does not establish preserved workbook layout, recalculated formulas or fixture accuracy.
getParserForMimeType; excelSheetToText, lines 109-129 · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/files/documents/crud.ts
LibreChat current Upload as Text guide librechat:librechat:r4-text-current
The development guide lists XLSX/XLS/ODS parsing up to 15 MB and token-bounded text injection, not a formatted spreadsheet editor.
Built-in parser; supported documents; truncation · documented · Source date not stated · Retrieved 2026-10-26
File upload in Microsoft Copilot microsoft-copilot:ms-upload
The support article names document/image/text formats and a limit of 20 files per conversation and 50 MB per file.
Supported file formats; file limits; files handling · documented · Source date not stated · Retrieved 2026-10-21
Projects librechat:librechat:projects
Projects persist files and instructions across a user’s chats but cannot be shared or transferred.
Availability; personal scope; files and instructions · documented · Source date not stated · Retrieved 2026-10-21
Get answers and insights about your Microsoft Copilot Notebook microsoft-copilot:ms-notebooks
Free Copilot Chat notebooks use up to 50 references; paid notebook grounding uses up to 300, with broader entity types.
Reference limits and supported content types · documented · Source date not stated · Retrieved 2026-10-21
Provide custom instructions for your Microsoft Copilot Notebook microsoft-copilot:ms-notebook-instructions
Notebook instructions can be edited and shared collaboratively; a SharePoint or OneDrive service plan is required.
Instructions; sharing note; prerequisites · documented · Source date not stated · Retrieved 2026-10-21
Agent Builder in Microsoft 365 Copilot microsoft-copilot:ms-builder
Agent Builder creates knowledge/instruction agents, has admin access controls and requires Copilot Studio for authored external actions.
Knowledge; licensing; admin controls; known limitations · documented · Source date 2026-09-30 · Retrieved 2026-10-21
SharePoint and OneDrive integration librechat:librechat:sharepoint
The Microsoft file picker uses Entra token reuse and delegated on-behalf-of downloads to attach files.
Prerequisites; delegated permissions; admin consent · documented · Source date not stated · Retrieved 2026-10-21
MCP librechat:librechat:mcp
MCP servers can be configured through YAML or the permission-gated UI, including per-user OAuth.
YAML/UI setup; authentication; ownership and selection · documented · Source date not stated · Retrieved 2026-10-21
MCP server configuration librechat:librechat:mcpcfg
Configuration includes stdio, SSE and Streamable HTTP transports and server-specific credentials.
Transport examples; headers; OAuth · documented · Source date not stated · Retrieved 2026-10-21
Data, Privacy, and Security for Microsoft Copilot microsoft-copilot:ms-privacy
Microsoft documents the rename, Graph permissions, protected interaction storage, no foundation-model training and residency exceptions.
Rename note; organizational data; stored interactions; EU Data Boundary · documented · Source date not stated · Retrieved 2026-10-21
Prerequisites for deploying connectors microsoft-copilot:ms-connector-license-r2
Paid Copilot/E7 supports connector grounding and federation; Studio/pay-as-you-go supports synced data in agents only, with no federated entitlement.
Licensing matrix; federated prerequisites; synced versus agents · documented · Source date 2026-06-02 · Retrieved 2026-10-21
Copilot connectors overview microsoft-copilot:ms-connectors-r2
Synced connectors index content/ACLs and provide citations; federation fetches live, while this October6 overview retains earlier read-only rollout wording.
Architecture; source examples; citations; October rollout note · documented · Source date 2026-10-06 · Retrieved 2026-10-21
Federated connectors overview microsoft-copilot:ms-federated-r2
The October16 detailed guide documents source-authorized writes and per-tool approval; Researcher stays read-only and Coming soon labels the admin Tools view.
Supported experiences; user licence; actions and confirmation; Tools view · documented · Source date 2026-10-16 · Retrieved 2026-10-21
Set up custom federated connectors microsoft-copilot:ms-custom-mcp-r2
Custom MCP prerequisites include create/update/delete tools; user access requires the Copilot licence and intersecting tenant/staging controls.
MCP prerequisites; OAuth; tenant controls and staged rollout · documented · Source date 2026-10-16 · Retrieved 2026-10-21
Self-serve sync connectors overview microsoft-copilot:ms-personal-sync-r2
Self-serve Confluence/Jira synchronization is a limited-preview per-user route with documented incremental/full crawl intervals.
Limited preview; Confluence/Jira; incremental/full synchronization · documented · Source date 2026-08-13 · Retrieved 2026-10-21
Set up Microsoft Copilot and assign licenses microsoft-copilot:ms-setup
IT assigns paid licences through M365; Microsoft documents Entra MFA, conditional access and additional Purview/SAM licensing dependencies.
Prerequisites; security; get started and deploy · documented · Source date not stated · Retrieved 2026-10-21
Microsoft Purview DLP for Microsoft 365 Copilot and Cowork microsoft-copilot:ms-dlp
Purview policies can detect sensitive prompt types and block Copilot processing; file-label and prompt paths have distinct conditions.
Sensitive information types; prevent processing prompts; sensitivity labels · documented · Source date not stated · Retrieved 2026-10-21
LibreChat Docker service configuration librechat:librechat:compose-pin
The pinned example runs a MongoDB primary store and a separate PGVector/RAG service with customer-mounted data.
docker-compose.yml, api/mongodb/vectordb/rag_api services · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path docker-compose.yml
User memory librechat:librechat:memory
Configured user memory stores cross-chat key/value context with user editing controls; it does not index all past chats.
Key/value store; controls; disabled by default · documented · Source date not stated · Retrieved 2026-10-21
Personalize what Microsoft Copilot remembers microsoft-copilot:ms-memory
Microsoft documents saved memories, prior-chat inferences, custom instructions and user removal controls, with work insights depending on plan.
Saved memory; history; work insights; custom instructions; temporary chat · documented · Source date not stated · Retrieved 2026-10-21
Get started with agents in the Microsoft Copilot app microsoft-copilot:ms-agents
Users can discover prebuilt and organization agents and share agent links, subject to account and organization settings.
Explore agents; create and share · documented · Source date not stated · Retrieved 2026-10-21
Image generation and editing librechat:librechat:images
Agents can use configured image tools for generation/editing; provider credentials and model parameters are separate.
OpenAI Image Tools; provider setup; admin configuration · documented · Source date not stated · Retrieved 2026-10-21
Web search librechat:librechat:web
Search can use Serper, SearXNG, Tavily or Keenable, with independently configured scraping and optional reranking.
Provider, scraper and reranker configuration · documented · Source date not stated · Retrieved 2026-10-21
Microsoft Copilot Chat Privacy and Protections microsoft-copilot:ms-chat-privacy
Copilot Chat has limited contextual work access, Exchange interaction logging, OneDrive uploads and a separate Bing web-query boundary.
Grounding; organizational data; logging; generated files; EUDB · documented · Source date 2026-08-24 · Retrieved 2026-10-21
Manage Microsoft Copilot Chat microsoft-copilot:ms-manage
The Allow web search policy can target the tenant, groups and users and also applies to paid Copilot.
Manage web search queries; Cloud Policy · documented · Source date not stated · Retrieved 2026-10-21
Scheduled Chats librechat:librechat:schedule
Opt-in experimental schedules execute saved Agents with cron/time zones and recheck access and balance before running.
Experimental and disabled by default; runtime and permissions · documented · Source date not stated · Retrieved 2026-10-21
Agents API beta librechat:librechat:api
The beta API exposes chat/Responses inference, Agent/Skill management and authenticated event delivery.
Inference; management; Agent Events; authentication · documented · Source date not stated · Retrieved 2026-10-21
Schedule your most used Copilot prompts microsoft-copilot:ms-schedule
Paid Copilot users can schedule up to ten prompts and edit, disable or delete schedules.
Prerequisites; create; manage scheduled prompts · documented · Source date not stated · Retrieved 2026-10-21
Get started with Copilot Cowork microsoft-copilot:ms-cowork
Cowork requires paid Copilot and enabled usage billing, exposes tool steps, and supports action approval and pause/cancel controls.
Prerequisites; watch Cowork work; approve actions · documented · Source date not stated · Retrieved 2026-10-21
Microsoft 365 Copilot Chat API overview microsoft-copilot:ms-chat-api-r2
The text Chat API preview requires each user to have the paid add-on, uses grounding/compliance, and excludes graphical/code/action skills.
Licensing; preview terms; limitations · documented · Source date 2026-07-02 · Retrieved 2026-10-21
Microsoft AI at Work roadmap microsoft-copilot:microsoft-copilot:r4-roadmap-work-iq
The roadmap describes Work IQ API public preview with MCP, REST and A2A access to work context. This does not establish that the separate Chat API is an MCP server or confirm endpoint/plan prerequisites.
April 30, Work IQ API public preview; October 15 legal announcement · vendor-claimed · Source date not stated · Retrieved 2026-10-26
Temporary chat and data retention librechat:librechat:retention
Operators configure expiry for chats/messages/files/shared links; normal chats do not expire by default and memories are excluded.
Default 30-day temporary retention; all/ephemeral; deadlines; memories · documented · Source date not stated · Retrieved 2026-10-21
Admin Insights librechat:librechat:insights
Insights reports persisted MongoDB activity and identifiable recent conversations; it is not monetary billing analytics.
Opt-in; capabilities; metrics; tenant scope · documented · Source date not stated · Retrieved 2026-10-21
Docker installation librechat:librechat:local
Docker self-installation runs LibreChat with its configured service dependencies.
Installation; configuration; updating · documented · Source date not stated · Retrieved 2026-10-21
Microsoft Copilot Chat usage report microsoft-copilot:ms-chat-usage
Unlicensed Copilot Chat usage is reported separately, anonymized by default, with per-user metrics and CSV export.
Audience; metrics; export · documented · Source date not stated · Retrieved 2026-10-21
Microsoft Copilot app deployment microsoft-copilot:microsoft-copilot:r4-mdm-deployment
The Windows Copilot installer can be distributed through Intune, Configuration Manager, Group Policy or another MDM. Automatic Microsoft 365 Apps installation has EEA/government/channel exclusions. The article confirms the Microsoft Copilot rename.
Deploy via any MDM; prevent automatic installation; rename note · documented · Source date not stated · Retrieved 2026-10-26
Get started writing prompts in Microsoft Copilot microsoft-copilot:ms-writing-r2
The support guide gives drafting and Word rewrite examples and separately requires the commercial Copilot subscription for work-data grounding.
Scope note; draft/edit examples; work-content licence · documented · Source date not stated · Retrieved 2026-10-21
Copilot Chat file-content translation microsoft-copilot:microsoft-copilot:r5-chat-translation
Documents can be attached/referenced for prompted translation in Copilot Chat. The page documents tone and audience instructions, not a formatting-preservation guarantee or managed terminology glossary.
Translate a file; tone/style/country examples · documented · Source date not stated · Retrieved 2026-10-26
Word Translator and Copilot translation workflow microsoft-copilot:microsoft-copilot:r5-word-translation-boundary
Word Translator creates a separate translated copy while retaining formatting; Copilot adapts wording, tone and audience. The page still asks users to review tables/layout after translation and does not make Translator the Copilot Chat engine.
Translate a Word document with Translator; Rewrite translated content with AI; Review checks · documented · Source date 2026-09-16 · Retrieved 2026-10-26
SharePoint document translation scope microsoft-copilot:microsoft-copilot:r5-sharepoint-translation
SharePoint/OneDrive document processing offers format/structure-preserving translated copies, with 40 MB limits and file/permission restrictions. It is a separate service from Copilot Chat.
Requirements; translated file copy; release limitations · documented · Source date 2026-04-23 · Retrieved 2026-10-26
SharePoint terminology glossary microsoft-copilot:microsoft-copilot:r5-sharepoint-glossary
Document processing accepts language-pair glossary files, including CSV/TSV/TAB/XLF, selected in its translation workflow. This does not establish a managed glossary in Copilot Chat.
Create and use a custom glossary for document translation · documented · Source date not stated · Retrieved 2026-10-26
Document processing separate metered billing microsoft-copilot:microsoft-copilot:r5-sharepoint-metering
Document processing uses an Azure subscription/resource group and a pay-as-you-go meter. A Copilot seat alone is not evidence that the separate glossary translation service is included.
Prerequisites; services list including document translation · documented · Source date 2025-08-04 · Retrieved 2026-10-26
Configure Microsoft Copilot settings microsoft-copilot:microsoft-copilot:r4-image-admin
Copilot Settings exposes an image-generation allow/prevent control. Available settings depend on licences, enabled features and rollout; AI Administrator is an example of the required admin role.
Configure Copilot actions; Before you begin · documented · Source date not stated · Retrieved 2026-10-26
Microsoft Product Terms for Online Services microsoft-copilot:microsoft-copilot:r4-online-service-terms
Commercial use is limited to the licensing agreement and Microsoft reserves other rights. Reverse engineering is restricted. Generative-AI output is Customer Data and Microsoft does not own it; this is not a component-by-component source-licence inventory.
Using the Online Services; Acceptable Use; Generative AI Output Content · documented · Source date not stated · Retrieved 2026-10-26
Speech configuration librechat:librechat:speech
Administrators configure audio provider engines and models separately from text generation.
Speech-to-text and text-to-speech engines · documented · Source date not stated · Retrieved 2026-10-21
LibreChat conversation-mode speech settings librechat:librechat:speech-conversation-r2
Conversation mode chains transcription, auto-send and TTS playback for hands-free turns after microphone activation; engines and audio routing are separately configured.
Speech Tab: conversationMode, autoTranscribeAudio, autoSendText, automaticPlayback; engine and allowedAddresses settings · documented · Source date not stated · Retrieved 2026-10-21
Get started with Copilot Voice microsoft-copilot:ms-voice
Work/school dictation and read-aloud are documented, while Voice availability varies and feedback audio is removed after 48 hours.
Feature/account matrix; work/school data and privacy · documented · Source date not stated · Retrieved 2026-10-21
Artifacts librechat:librechat:artifacts
Artifacts render generated React, HTML and Mermaid content in the chat interface.
React, HTML and Mermaid previews · documented · Source date not stated · Retrieved 2026-10-21
Code interpreter security architecture microsoft-copilot:ms-code-r2
Code interpreter in Copilot/eligible declarative agents runs Python analysis and charts in session-isolated Azure VMs with no network traffic.
Availability; isolated Azure VM; Python analysis · documented · Source date 2025-11-26 · Retrieved 2026-10-21
Copilot Chat privacy and protections microsoft-copilot:ms-chat-privacy-r2
Managed work Chat logs prompts/responses in Exchange and places uploads in OneDrive for Business; generated Office files have separate download/storage paths.
Exchange logging; OneDrive uploads; Office file generation · documented · Source date 2026-08-24 · Retrieved 2026-10-21
Shareable links librechat:librechat:share
Shared links publish a transcript branch and optional file snapshots independently of the owner’s live file ACL.
Authentication defaults; file snapshots; continuation · documented · Source date not stated · Retrieved 2026-10-21
LibreChat locale registration librechat:librechat:i18n-pin
The pinned client registers English, German, French and Italian translations among its supported locales.
client/src/locales/i18n.ts, language resources · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path client/src/locales/i18n.ts
Supported languages for Microsoft Copilot microsoft-copilot:ms-language
The supported work/school language list includes English, German, French and Italian, with localization asserted by Microsoft.
Work or school accounts; localization description · documented · Source date not stated · Retrieved 2026-10-21
Authentication system librechat:librechat:auth
Local/LDAP accounts can be required to use TOTP; federated MFA belongs to the identity provider and account creation/deletion scripts are documented.
Required two-factor authentication; Registration; User scripts · documented · Source date not stated · Retrieved 2026-10-21
OAuth2 and OIDC librechat:librechat:openid
LibreChat documents OAuth2/OIDC providers including Microsoft Entra, Google, Keycloak and Auth0.
Supported providers; setup · documented · Source date not stated · Retrieved 2026-10-21
SAML authentication librechat:librechat:saml
SAML is a documented authentication option for the self-hosted application.
Overview and requirements · documented · Source date not stated · Retrieved 2026-10-21
Azure Entra authentication librechat:librechat:entra
Entra OIDC supports group-based admission and Graph integration using configured scopes and token reuse.
Group claims; token reuse; Microsoft Graph integration · documented · Source date not stated · Retrieved 2026-10-21
Set up usage-based billing for Copilot Credits microsoft-copilot:ms-cost-setup
The cost dashboard exposes policy and per-user monthly limits and consumes prepaid credit before PAYG overage.
Roles; monthly limits; prepaid and PAYG · documented · Source date not stated · Retrieved 2026-10-21
Token usage librechat:librechat:tokens
Usage and estimated costs use recorded tokens and configured provider rates; transactions are distinct from balance enforcement.
Context cost; transactions; per-endpoint token rates · documented · Source date not stated · Retrieved 2026-10-21
Microsoft Copilot usage report microsoft-copilot:ms-usage
The paid report tracks adoption and application activity and hides identifying user, group and site fields by default.
Report metrics and privacy note · documented · Source date not stated · Retrieved 2026-10-21
Logging librechat:librechat:logging
Backend operational logs are written to customer files and can feed external tools; the guide describes 14-day rotation rather than a compliance archive.
Error/debug logs; rotation; external tools · documented · Source date not stated · Retrieved 2026-10-21
Audit logs for Copilot and AI applications microsoft-copilot:ms-audit
Enabled Purview Audit records Copilot admin changes, users, accessed resources, agent identifiers and policy metadata.
Admin and user activities; common properties · documented · Source date not stated · Retrieved 2026-10-21
Learn about auditing solutions in Microsoft Purview microsoft-copilot:ms-audit-standard
Purview distinguishes standard audit retention from separately licensed longer-retention capabilities.
Audit Standard and Premium retention · documented · Source date not stated · Retrieved 2026-10-21
Learn about retention for Copilot and AI apps microsoft-copilot:ms-retention
Copilot interaction copies live in hidden Exchange folders, can have Purview retention policies and remain subject to legal holds.
What is included; mailbox retention flow; holds · documented · Source date not stated · Retrieved 2026-10-21
Audit logs for Copilot and AI applications microsoft-copilot:microsoft-copilot:r4-audit-export
Purview supports searching and exporting Copilot audit events, then filtering exported AppIdentity values. This is metadata export, not a claim that audit events contain full prompts and responses.
Accessing Copilot audit logs; Next steps · documented · Source date 2026-08-26 · Retrieved 2026-10-26
Microsoft 365 usage reports in Microsoft Graph microsoft-copilot:microsoft-copilot:r4-audit-api
The document identifies EXO Search-UnifiedAuditLog CSV export and Office 365 Management Activity API streaming to SIEM for CopilotInteraction events. It distinguishes these from Graph usage-report APIs.
Programmatically export unlicensed Copilot Chat usage · documented · Source date 2025-12-23 · Retrieved 2026-10-26
LibreChat development content-filter configuration librechat:librechat:r4-content-filter
Opt-in base-YAML policies inspect selected message/file content; block and audit differ from limited Agent text redaction. This is development documentation, not a hosted DLP assurance.
Source-Aware Filters; Pattern Configuration; Redaction; File Fields · documented · Source date not stated · Retrieved 2026-10-26
LibreChat content-inspection runtime librechat:librechat:r4-pii-runtime
Source-aware configured inspection executes in the LibreChat API. Missing policy disables that scope; configured actions and fields bound inspection.
createConfiguredContentInspector; source rule configuration · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/runtime.ts
LibreChat pattern detector librechat:librechat:r4-patterns
Default starter patterns detect credential-shaped tokens/headers. Operator custom patterns use bounded regular expressions; a generic comprehensive PII classifier is not established.
STARTER_PATTERNS; configured RE2JS rules · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/detectors/pattern.ts
LibreChat private text submission librechat:librechat:r4-private-submission
The private text ingress permits configured redaction only on eligible fresh interactive Agent text. Original content is encrypted; edit/resume/file paths do not gain blanket redaction.
createPrivateTextIngress; fresh Agent text and clientRequestId checks · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/protection/private/submission.ts
LibreChat API content-filter middleware librechat:librechat:r4-filter-middleware
The server middleware applies configured inspection and rejects blocked/uninspectable requests with HTTP 400. No deployment or detection fixture was run.
createMessageFilterPii; contentFilterBlockResponse; uninspectable response · source-inspected · Source date 2026-10-24 · Retrieved 2026-10-26
Commit a378657583567310c841d652b0f6b00c83e2bd6b, path packages/api/src/middleware/messageFilterPii.ts
LibreChat config v1.3.18 changelog librechat:librechat:r4-config-1318
Dated development config changes add limited Agent text redaction and ephemeral retention mode. These are not a promise of universal redaction or a vendor zero-retention contract.
October 22, 2026; opt-in PII redaction; retention mode · documented · Source date 2026-10-22 · Retrieved 2026-10-26
Learn about the default DLP policy for Microsoft 365 Copilot location microsoft-copilot:ms-dlp-default
The default sensitive-prompt DLP policy simulates and alerts rather than blocking until configured otherwise.
Simulation mode default · documented · Source date not stated · Retrieved 2026-10-21
Purview DLP for Copilot and Cowork microsoft-copilot:microsoft-copilot:r4-custom-dlp-types
Prompt blocking supports built-in and custom sensitive-information types in preview with tenant rollout caveats. Uploaded-file contents are not scanned by this Copilot DLP location.
Block sensitive information types in prompts; Files uploaded in prompts; Availability · documented · Source date not stated · Retrieved 2026-10-26
Interface configuration librechat:librechat:interface
Administrators configure UI feature permissions and usage terms in the self-hosted deployment.
Feature permissions; custom welcome and terms · documented · Source date not stated · Retrieved 2026-10-21
Remote hosting librechat:librechat:remote
The application can be deployed on customer-selected remote servers with operator-managed security.
Hosting options; security considerations · documented · Source date not stated · Retrieved 2026-10-21
Enterprise data protection in Microsoft Copilot and Microsoft Copilot Chat microsoft-copilot:ms-edp
Enterprise data protection applies Microsoft DPA/Product Terms and documents encryption and tenant separation.
DPA; protection of prompts and responses · documented · Source date not stated · Retrieved 2026-10-21
What is the EU Data Boundary? microsoft-copilot:ms-eudb
The EU/EFTA boundary covers customer data and pseudonymized personal logs subject to transfer exceptions, with professional-services data committed at rest.
Overview; logs; countries; configuration · documented · Source date 2025-02-26 · Retrieved 2026-10-21
LibreChat Demo terms librechat:librechat:demo
The free hosted Demo is offered as-is with possible data cleanups and no durable business-service guarantee.
Evaluation scope; retention; disclaimer · documented · Source date 2026-03-12 · Retrieved 2026-10-21
Microsoft Copilot no-training statement microsoft-copilot:ms-no-training
Microsoft states that prompts, responses and Graph data do not train foundation models and that the Copilot service opts out of Azure OpenAI abuse monitoring.
Important; abuse monitoring · vendor-claimed · Source date not stated · Retrieved 2026-10-21
Personal settings librechat:librechat:settings
Users configure interface language, audio and personal data controls.
Language; speech; data controls · documented · Source date not stated · Retrieved 2026-10-21
Learn about retention for Copilot and AI apps microsoft-copilot:ms-retention-r2
Purview governs Exchange copies of AI interactions and holds, with asynchronous deletion processing distinct from uploaded-file storage.
Interaction storage; retention/hold processing; deleted users · documented · Source date 2025-09-26 · Retrieved 2026-10-21
ClickHouse acquisition of LibreChat librechat:librechat:owner
ClickHouse announced the acquisition of LibreChat and that Danny Avila and the team joined ClickHouse.
Announcement, November 4, 2025 · documented · Source date 2025-11-04 · Retrieved 2026-10-21
Overview of AI Subprocessors microsoft-copilot:ms-subprocessors
Microsoft links its Online Services Subprocessors List and subscriptions for change notifications.
Subprocessor governance; customer notification · documented · Source date 2026-08-18 · Retrieved 2026-10-21
Microsoft Service Trust Portal access microsoft-copilot:microsoft-copilot:r4-report-access
Microsoft publishes external audit reports and third-party penetration-test attestations in STP; some downloads require an Entra organization account and acceptance of the compliance-material NDA. No report was downloaded.
Accessing the Service Trust Portal; Reports, Whitepapers and Artifacts · documented · Source date not stated · Retrieved 2026-10-26
BSI certificate registry: Microsoft 365 ISMS IS 552878 microsoft-copilot:microsoft-copilot:r5-bsi-iso27001
BSI registry verifies Microsoft Corporation IS 552878 for the Microsoft 365 services ISMS, development, operations and PII protection, with a February 14, 2024 applicability statement. It does not name Copilot separately.
ISO/IEC 27001:2022; Microsoft Corporation; scope and effective/expiry dates · certificate-verified · Source date 2024-07-26 · Retrieved 2026-10-26
Issuer: BSI. Scope: Microsoft Corporation; Microsoft 365 services ISMS, development, operations and PII protection; Statement of Applicability dated 2024-02-14. No explicit Copilot-specific scope list was obtained from this registry entry.. Valid 2024-07-29 to 2027-07-28
BSI certificate registry: Microsoft 365 privacy PM 741035 microsoft-copilot:microsoft-copilot:r5-bsi-iso27701
BSI verifies the Microsoft 365 services processor privacy-management scope, referring to IS 552878 and the February 14, 2024 applicability statement. Copilot-specific applicability is not independently enumerated.
ISO/IEC 27701:2019; processor scope; effective/expiry dates · certificate-verified · Source date 2024-07-26 · Retrieved 2026-10-26
Issuer: BSI. Scope: Microsoft Corporation; Microsoft 365 services ISMS, development, operations, support and PII protection as a processor; Statement of Applicability dated 2024-02-14; references IS 552878. Not a separately enumerated Copilot certificate.. Valid 2024-07-29 to 2027-07-28
Copilot Microsoft 365 compliance relationship microsoft-copilot:microsoft-copilot:r5-copilot-compliance-boundary
Microsoft includes Copilot in its existing Microsoft 365 privacy/security/compliance commitments and lists ISO 27001/42001. This is vendor scope documentation, not the issuer’s Copilot-specific certificate schedule.
Meeting regulatory compliance requirements · documented · Source date not stated · Retrieved 2026-10-26
Microsoft public ISO 42001 service scope microsoft-copilot:microsoft-copilot:r5-iso42001-scope
Microsoft explicitly lists Copilot and Copilot Chat in its ISO 42001 service scope. The public page points to STP but does not provide an issuer/certificate validity interval for those products.
Microsoft AI services in scope; report route · vendor-claimed · Source date 2026-09-11 · Retrieved 2026-10-26
LibreChat website privacy policy librechat:librechat:siteprivacy
Website, demo and self-hosted software are distinct privacy scopes; website terms do not establish a customer deployment DPA.
Scope and exclusions · documented · Source date not stated · Retrieved 2026-10-21
LibreChat v0.8.8 message storage schema librechat:librechat:secrecy-message-pin
The pinned Mongoose schema declares message text as a String and content as mixed fields; this source does not establish operator exclusion from live content.
packages/data-schemas/src/schema/message.ts, text at lines 55-58 and content at lines 139-143 · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path packages/data-schemas/src/schema/message.ts
LibreChat Demo privacy policy librechat:librechat:secrecy-demo-policy
The Demo policy describes model-provider transmission and contractual processor instruction/security duties for the Demo; it does not cover a customer self-hosted deployment.
Scope; section 4 Third-Party AI Model Providers; section 6 Data Sharing and Sub-Processors · documented · Source date 2026-03-12 · Retrieved 2026-10-21
Microsoft Copilot - Pläne und Preise für Unternehmen microsoft-copilot:ms-price-de
The German page lists EUR 26 per user per month billed annually excluding VAT, plus a qualifying M365 subscription.
Paid Microsoft 365 Copilot price card and tax notice · vendor-claimed · Source date not stated · Retrieved 2026-10-21
Billing rates and management microsoft-copilot:ms-credit-rates
Studio billing uses feature-dependent credits, with qualifying paid-user assistive scenarios listed at no charge.
Copilot Credits billing table · documented · Source date not stated · Retrieved 2026-10-21
Azure Retail Prices, Switzerland North Linux VMs librechat:librechat:cost-vm
EUR hourly PAYG rates retrieved 2026-10-21 are 0.2226, 0.4453 and 0.8905 for D4s, D8s and D16s v5 respectively.
Consumption; Virtual Machines Dsv5 Series; Standard_D4s_v5/D8s_v5/D16s_v5 · documented · Source date not stated · Retrieved 2026-10-21
Azure Retail Prices, PostgreSQL Flexible Server librechat:librechat:cost-pg
EUR hourly PAYG GP compute is 0.2288, 0.4576 and 0.9152 for 2/4/8 vCore; storage is EUR 0.1325 per GB-month.
General Purpose Ddsv5 Series Compute, 2/4/8 vCore; Flex Server Storage · documented · Source date not stated · Retrieved 2026-10-21
ECB euro reference rate history librechat:librechat:cost-fx
The 2026-10-20 reference rates are EUR 1 = USD 1.1215 and CHF 0.9237.
Cube time=2026-10-20; USD and CHF · documented · Source date 2026-10-20 · Retrieved 2026-10-21
OpenAI API pricing librechat:librechat:cost-model
Standard gpt-6-luna API price is USD 0.10 per million input tokens and USD 0.50 per million output tokens; caching, batch and regional premiums are separate.
Standard, short-context gpt-6-luna row · documented · Source date not stated · Retrieved 2026-10-21
GPT-6 Luna model documentation librechat:librechat:cost-effort
The model accepts reasoning effort none, the lowest documented effort, and lists the same standard text-token rates.
Reasoning effort and text-token pricing · documented · Source date not stated · Retrieved 2026-10-21
Euro foreign exchange reference rates microsoft-copilot:fx-20261020
ECB historical XML retrieved directly confirms EUR 1 = USD 1.1215 and CHF 0.9237 for 2026-10-20.
Cube time=2026-10-20; USD and CHF entries · documented · Source date 2026-10-20 · Retrieved 2026-10-21
LibreChat conversation export implementation librechat:librechat:export-pin
The pinned user conversation exporter supports JSON, CSV, Markdown and text, plus screenshot export.
client/src/hooks/Conversations/useExportConversation.ts, export dispatch · source-inspected · Source date not stated · Retrieved 2026-10-21
Commit e8f3be08623663d4ad7f7241e693c94469b63bb0, path client/src/hooks/Conversations/useExportConversation.ts
Copilot support and feedback microsoft-copilot:microsoft-copilot:r4-support-channels
Copilot extensibility support directs general questions to Microsoft Q&A and service/development issues to Admin Center Help and Support; service requests depend on Premier/Unified support agreement.
Developer support channels · documented · Source date 2026-01-22 · Retrieved 2026-10-26
Microsoft Copilot Skilling Center microsoft-copilot:ms-training
Microsoft publishes admin and user learning resources and links its Champion programme.
Role-based resources; Academy; Champions · vendor-claimed · Source date not stated · Retrieved 2026-10-21